Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6183 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.7079. Min Act: -0.1700
Data Index: 5963943 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.5516. Min Act: -0.1700
Data Index: 1998396 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.5516. Min Act: -0.1700
Data Index: 4726285 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.5204. Min Act: -0.1700
Data Index: 439709 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.5516. Min Act: -0.1700
Data Index: 3775060 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4891. Min Act: -0.1700
Data Index: 4458864 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4891. Min Act: -0.1700
Data Index: 8777417 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4579. Min Act: -0.1700
Data Index: 6017099 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4579. Min Act: -0.1700
Data Index: 4534003 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4579. Min Act: -0.1700
Data Index: 822386 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4266. Min Act: -0.1700
Data Index: 8705504 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4266. Min Act: -0.1700
Data Index: 2751566 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.4266. Min Act: -0.1700
Data Index: 5342628 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3641. Min Act: -0.1700
Data Index: 1698031 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3641. Min Act: -0.1700
Data Index: 2766039 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3641. Min Act: -0.1700
Data Index: 7065006 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3329. Min Act: -0.1700
Data Index: 6297815 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3641. Min Act: -0.1700
Data Index: 7115772 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.2704. Min Act: -0.1700
Data Index: 310372 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7079. Min Range: -6.7079
Max Act: 6.3016. Min Act: -0.1700
Data Index: 2021059 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19