Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.9463. Min Act: -0.1700
Data Index: 6506188 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.9150. Min Act: -0.1700
Data Index: 2817976 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1844501 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8838. Min Act: -0.1700
Data Index: 998253 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8525. Min Act: -0.1700
Data Index: 2125183 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8525. Min Act: -0.1700
Data Index: 8195526 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8212. Min Act: -0.1700
Data Index: 1572096 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8212. Min Act: -0.1700
Data Index: 6124587 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.8212. Min Act: -0.1700
Data Index: 4993903 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7900. Min Act: -0.1700
Data Index: 6409583 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8204456 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 7359322 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 343826 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8272462 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 6466773 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7274. Min Act: -0.1700
Data Index: 6449253 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 4399864 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 6449252 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 3430219 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9463. Min Range: -3.9463
Max Act: 3.7587. Min Act: -0.1700
Data Index: 5902940 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19