Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0292. Min Range: -3.0292
Max Act: 3.0292. Min Act: -0.1700
Data Index: 5987931 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.8867. Min Act: -0.1700
Data Index: 1631843 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.8709. Min Act: -0.1700
Data Index: 6695621 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.8073. Min Act: -0.1700
Data Index: 1222050 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.8073. Min Act: -0.1700
Data Index: 3336768 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 724747 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 2593956 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7435. Min Act: -0.1700
Data Index: 8393737 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7435. Min Act: -0.1700
Data Index: 203031 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 14242 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 6291346 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 318095 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 7880001 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7115. Min Act: -0.1700
Data Index: 6838022 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7115. Min Act: -0.1700
Data Index: 4118495 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 6244118 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7435. Min Act: -0.1700
Data Index: 4247677 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 2997572 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 3711371 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0292. Min Range: -3.0292
Max Act: 2.7275. Min Act: -0.1700
Data Index: 6521410 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19