Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.6111. Min Act: -0.1700
Data Index: 2017777 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.6111. Min Act: -0.1700
Data Index: 6690424 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.6111. Min Act: -0.1700
Data Index: 5467983 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5798. Min Act: -0.1700
Data Index: 4549374 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5486. Min Act: -0.1700
Data Index: 6736719 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5486. Min Act: -0.1700
Data Index: 8757630 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5798. Min Act: -0.1700
Data Index: 5976292 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5486. Min Act: -0.1700
Data Index: 4297407 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4861. Min Act: -0.1700
Data Index: 7435319 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5173. Min Act: -0.1700
Data Index: 8211676 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.5173. Min Act: -0.1700
Data Index: 7233891 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4861. Min Act: -0.1700
Data Index: 7931848 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4548. Min Act: -0.1700
Data Index: 8070737 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4236. Min Act: -0.1700
Data Index: 8444913 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.3923. Min Act: -0.1700
Data Index: 4855268 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4236. Min Act: -0.1700
Data Index: 6026834 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.4236. Min Act: -0.1700
Data Index: 2577992 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.3923. Min Act: -0.1700
Data Index: 375170 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.3923. Min Act: -0.1700
Data Index: 1176491 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6111. Min Range: -4.6111
Max Act: 4.3923. Min Act: -0.1700
Data Index: 6580111 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19