Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.7510. Min Act: -0.1700
Data Index: 6291240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.6572. Min Act: -0.1700
Data Index: 7596404 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.5947. Min Act: -0.1700
Data Index: 5458944 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.5010. Min Act: -0.1700
Data Index: 6202930 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.4697. Min Act: -0.1700
Data Index: 8650448 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3760. Min Act: -0.1700
Data Index: 2625270 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3760. Min Act: -0.1700
Data Index: 7958800 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3760. Min Act: -0.1700
Data Index: 2625257 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3447. Min Act: -0.1700
Data Index: 7937451 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3135. Min Act: -0.1700
Data Index: 369541 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.3135. Min Act: -0.1700
Data Index: 7059084 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2822. Min Act: -0.1700
Data Index: 4388651 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2510. Min Act: -0.1700
Data Index: 548694 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2822. Min Act: -0.1700
Data Index: 2476751 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2822. Min Act: -0.1700
Data Index: 2517835 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2510. Min Act: -0.1700
Data Index: 6960985 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.2510. Min Act: -0.1700
Data Index: 3029809 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.1885. Min Act: -0.1700
Data Index: 5410955 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.1572. Min Act: -0.1700
Data Index: 6233394 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7510. Min Range: -5.7510
Max Act: 5.1885. Min Act: -0.1700
Data Index: 1775665 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19