Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4609 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2583. Min Act: -0.1700
Data Index: 1932610 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2270. Min Act: -0.1700
Data Index: 1015267 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.2583. Min Act: -0.1700
Data Index: 146098 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.1958. Min Act: -0.1700
Data Index: 6597056 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0707. Min Act: -0.1700
Data Index: 939861 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0707. Min Act: -0.1700
Data Index: 4590848 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0395. Min Act: -0.1700
Data Index: 4060779 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0395. Min Act: -0.1700
Data Index: 8112884 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0395. Min Act: -0.1700
Data Index: 5050612 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2583. Min Range: -4.2583
Max Act: 4.0082. Min Act: -0.1700
Data Index: 4201098 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9770. Min Act: -0.1700
Data Index: 3063465 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9770. Min Act: -0.1700
Data Index: 6647456 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 3193675 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9144. Min Act: -0.1700
Data Index: 1983718 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1211027 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9770. Min Act: -0.1700
Data Index: 3253109 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 485204 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1033004 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1983719 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2583. Min Range: -4.2583
Max Act: 3.9457. Min Act: -0.1700
Data Index: 5751356 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19