Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5007 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.7379. Min Act: -0.1700
Data Index: 2415614 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.6442. Min Act: -0.1700
Data Index: 8185312 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.5192. Min Act: -0.1700
Data Index: 3658955 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.4879. Min Act: -0.1700
Data Index: 2573040 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.4567. Min Act: -0.1700
Data Index: 1755862 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.4254. Min Act: -0.1700
Data Index: 4823018 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.3942. Min Act: -0.1700
Data Index: 3561464 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.3629. Min Act: -0.1700
Data Index: 7663600 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.3004. Min Act: -0.1700
Data Index: 6141171 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.3004. Min Act: -0.1700
Data Index: 5637282 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.2379. Min Act: -0.1700
Data Index: 2636556 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7039839 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.2067. Min Act: -0.1700
Data Index: 4001301 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.1754. Min Act: -0.1700
Data Index: 6570768 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.1442. Min Act: -0.1700
Data Index: 3721188 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.1129. Min Act: -0.1700
Data Index: 1143571 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.1129. Min Act: -0.1700
Data Index: 2762395 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.0817. Min Act: -0.1700
Data Index: 197800 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.0817. Min Act: -0.1700
Data Index: 3953263 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7379. Min Range: -6.7379
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7464419 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19