Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.0655. Min Range: -12.0655
Max Act: 12.0655. Min Act: -0.1700
Data Index: 4048301 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0655. Min Range: -12.0655
Max Act: 12.0655. Min Act: -0.1700
Data Index: 2820270 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.9405. Min Act: -0.1700
Data Index: 1698700 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0655. Min Range: -12.0655
Max Act: 12.0030. Min Act: -0.1700
Data Index: 7678697 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.9405. Min Act: -0.1700
Data Index: 2820271 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8780. Min Act: -0.1700
Data Index: 5893647 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8780. Min Act: -0.1700
Data Index: 4253493 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8780. Min Act: -0.1700
Data Index: 2176012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8780. Min Act: -0.1700
Data Index: 6645452 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8155. Min Act: -0.1700
Data Index: 4587731 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8155. Min Act: -0.1700
Data Index: 2380767 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.7530. Min Act: -0.1700
Data Index: 505720 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8155. Min Act: -0.1700
Data Index: 6412041 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.8155. Min Act: -0.1700
Data Index: 7643480 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.7530. Min Act: -0.1700
Data Index: 1290274 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.7530. Min Act: -0.1700
Data Index: 5159961 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.7530. Min Act: -0.1700
Data Index: 1620172 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.6905. Min Act: -0.1700
Data Index: 2820269 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.6905. Min Act: -0.1700
Data Index: 1457077 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0655. Min Range: -12.0655
Max Act: 11.6280. Min Act: -0.1700
Data Index: 5340222 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19