Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4886 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.2959. Min Act: -0.1700
Data Index: 5576529 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.2334. Min Act: -0.1700
Data Index: 2339798 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 72256 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 4144996 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 8197086 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 2168401 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 7819464 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 2615925 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.1084. Min Act: -0.1700
Data Index: 3667020 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.0459. Min Act: -0.1700
Data Index: 6440474 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2959. Min Range: -7.2959
Max Act: 7.0459. Min Act: -0.1700
Data Index: 7043646 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9834. Min Act: -0.1700
Data Index: 7572291 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9521. Min Act: -0.1700
Data Index: 3418404 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9834. Min Act: -0.1700
Data Index: 5787822 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9834. Min Act: -0.1700
Data Index: 3292440 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9834. Min Act: -0.1700
Data Index: 4322811 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9521. Min Act: -0.1700
Data Index: 1158921 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9209. Min Act: -0.1700
Data Index: 1005542 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9209. Min Act: -0.1700
Data Index: 242001 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2959. Min Range: -7.2959
Max Act: 6.9209. Min Act: -0.1698
Data Index: 223362 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19