Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.2117. Min Act: -0.1700
Data Index: 7524054 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.1492. Min Act: -0.1700
Data Index: 7208676 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.0867. Min Act: -0.1700
Data Index: 2069646 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.0554. Min Act: -0.1700
Data Index: 189338 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 123015 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.0242. Min Act: -0.1700
Data Index: 3242003 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 1395540 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2117. Min Range: -4.2117
Max Act: 4.0242. Min Act: -0.1700
Data Index: 1527276 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9616. Min Act: -0.1700
Data Index: 5147897 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 2900976 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9929. Min Act: -0.1700
Data Index: 6882907 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9616. Min Act: -0.1700
Data Index: 111590 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9616. Min Act: -0.1700
Data Index: 2756354 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.9304. Min Act: -0.1700
Data Index: 7917563 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8991. Min Act: -0.1700
Data Index: 8307173 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8991. Min Act: -0.1700
Data Index: 3436631 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8991. Min Act: -0.1700
Data Index: 5421202 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8991. Min Act: -0.1700
Data Index: 5043774 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8678. Min Act: -0.1700
Data Index: 6205263 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2117. Min Range: -4.2117
Max Act: 3.8835. Min Act: -0.1700
Data Index: 2373817 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19