Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.2207. Min Act: -0.1700
Data Index: 8361602 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.1263. Min Act: -0.1700
Data Index: 633728 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.1263. Min Act: -0.1700
Data Index: 4633396 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.0790. Min Act: -0.1700
Data Index: 938107 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.0159. Min Act: -0.1700
Data Index: 7581716 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2207. Min Range: -3.2207
Max Act: 3.0001. Min Act: -0.1700
Data Index: 4215597 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9685. Min Act: -0.1700
Data Index: 5210292 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9685. Min Act: -0.1700
Data Index: 779919 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9843. Min Act: -0.1700
Data Index: 5495671 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9527. Min Act: -0.1700
Data Index: 1590351 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9527. Min Act: -0.1700
Data Index: 1859730 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9368. Min Act: -0.1700
Data Index: 984126 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9210. Min Act: -0.1700
Data Index: 3670571 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9210. Min Act: -0.1700
Data Index: 6585389 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9051. Min Act: -0.1700
Data Index: 2068773 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.8734. Min Act: -0.1700
Data Index: 3670570 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.9210. Min Act: -0.1700
Data Index: 984124 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.8734. Min Act: -0.1700
Data Index: 4519837 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.8734. Min Act: -0.1700
Data Index: 5514068 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2207. Min Range: -3.2207
Max Act: 2.8734. Min Act: -0.1700
Data Index: 7160196 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19