Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.3784. Min Act: -0.1700
Data Index: 2687977 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.2221. Min Act: -0.1700
Data Index: 1723500 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.2534. Min Act: -0.1700
Data Index: 4619440 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.2534. Min Act: -0.1700
Data Index: 7259783 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1596. Min Act: -0.1700
Data Index: 1626415 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1284. Min Act: -0.1700
Data Index: 1722586 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8186223 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0971. Min Act: -0.1700
Data Index: 2573671 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0971. Min Act: -0.1700
Data Index: 5718815 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0971. Min Act: -0.1700
Data Index: 6072289 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0659. Min Act: -0.1700
Data Index: 7515620 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 2967402 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 1439323 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 2130217 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 1206987 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 1585462 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 7148993 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 3076277 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 1888857 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3784. Min Range: -5.3784
Max Act: 4.9409. Min Act: -0.1700
Data Index: 5671015 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19