Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2541. Min Range: -6.2541
Max Act: 6.2541. Min Act: -0.1700
Data Index: 736852 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2541. Min Range: -6.2541
Max Act: 6.1291. Min Act: -0.1700
Data Index: 504410 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2541. Min Range: -6.2541
Max Act: 6.0978. Min Act: -0.1700
Data Index: 2727513 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2541. Min Range: -6.2541
Max Act: 6.0041. Min Act: -0.1700
Data Index: 1083091 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9416. Min Act: -0.1700
Data Index: 3596209 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9728. Min Act: -0.1700
Data Index: 6072831 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9416. Min Act: -0.1700
Data Index: 2315046 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9728. Min Act: -0.1700
Data Index: 6072837 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9103. Min Act: -0.1700
Data Index: 6180393 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9103. Min Act: -0.1700
Data Index: 3360453 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9103. Min Act: -0.1700
Data Index: 682368 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8791. Min Act: -0.1700
Data Index: 5691227 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8791. Min Act: -0.1700
Data Index: 8588018 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.9103. Min Act: -0.1700
Data Index: 4561582 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8478. Min Act: -0.1700
Data Index: 2982876 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8791. Min Act: -0.1700
Data Index: 8159464 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6072828 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8478. Min Act: -0.1700
Data Index: 6753934 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8478. Min Act: -0.1700
Data Index: 8632513 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2541. Min Range: -6.2541
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6072845 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19