Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1265 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 3151967 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3856. Min Act: -0.1700
Data Index: 7077453 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.3543. Min Act: -0.1700
Data Index: 7049791 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2918. Min Act: -0.1700
Data Index: 4618048 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2606. Min Act: -0.1700
Data Index: 8365393 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1981. Min Act: -0.1700
Data Index: 2543076 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2293. Min Act: -0.1700
Data Index: 4348378 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1668. Min Act: -0.1700
Data Index: 5420411 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1668. Min Act: -0.1700
Data Index: 5297039 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 3101687 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 4182697 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 8126278 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 5833046 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 980134 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 185341 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 4998811 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 4631704 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 4187781 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 1451483 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 2352321 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19