Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4556 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.8179. Min Act: -0.1700
Data Index: 2003825 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.6304. Min Act: -0.1700
Data Index: 5911929 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.5679. Min Act: -0.1700
Data Index: 1762371 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.4742. Min Act: -0.1700
Data Index: 4486497 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.4429. Min Act: -0.1700
Data Index: 3443433 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.4429. Min Act: -0.1700
Data Index: 5681523 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.4117. Min Act: -0.1700
Data Index: 5275731 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.4117. Min Act: -0.1700
Data Index: 2588272 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.3804. Min Act: -0.1700
Data Index: 5595951 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.3804. Min Act: -0.1700
Data Index: 1276563 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.3492. Min Act: -0.1700
Data Index: 6366478 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.3179. Min Act: -0.1700
Data Index: 6590881 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.3179. Min Act: -0.1700
Data Index: 6423996 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2554. Min Act: -0.1700
Data Index: 2973897 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2554. Min Act: -0.1700
Data Index: 3948775 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2867. Min Act: -0.1700
Data Index: 3765936 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2867. Min Act: -0.1700
Data Index: 246339 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2554. Min Act: -0.1700
Data Index: 2833291 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2554. Min Act: -0.1700
Data Index: 5911752 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8179. Min Range: -5.8179
Max Act: 5.2554. Min Act: -0.1700
Data Index: 6389988 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19