Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2283. Min Range: -4.2283
Max Act: 4.2283. Min Act: -0.1700
Data Index: 3669989 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2283. Min Range: -4.2283
Max Act: 4.1033. Min Act: -0.1700
Data Index: 6001121 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2283. Min Range: -4.2283
Max Act: 4.0095. Min Act: -0.1700
Data Index: 3624556 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2283. Min Range: -4.2283
Max Act: 4.0095. Min Act: -0.1700
Data Index: 6934699 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9783. Min Act: -0.1700
Data Index: 3832508 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9783. Min Act: -0.1700
Data Index: 3832506 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9783. Min Act: -0.1700
Data Index: 3832502 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9470. Min Act: -0.1700
Data Index: 3832509 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9470. Min Act: -0.1700
Data Index: 498216 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9158. Min Act: -0.1700
Data Index: 6399623 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.9158. Min Act: -0.1700
Data Index: 6762714 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8845. Min Act: -0.1700
Data Index: 3832510 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8845. Min Act: -0.1700
Data Index: 4131166 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8532. Min Act: -0.1700
Data Index: 4393178 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8532. Min Act: -0.1700
Data Index: 8374634 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8845. Min Act: -0.1700
Data Index: 7416000 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8845. Min Act: -0.1700
Data Index: 7825240 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8532. Min Act: -0.1700
Data Index: 5828007 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8532. Min Act: -0.1700
Data Index: 908160 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2283. Min Range: -4.2283
Max Act: 3.8532. Min Act: -0.1700
Data Index: 7052465 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19