Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4847. Min Range: -6.4847
Max Act: 6.4847. Min Act: -0.1700
Data Index: 728646 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.9847. Min Act: -0.1700
Data Index: 3275995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.7972. Min Act: -0.1700
Data Index: 7150436 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.7659. Min Act: -0.1700
Data Index: 4843085 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.7034. Min Act: -0.1700
Data Index: 5486994 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.6409. Min Act: -0.1700
Data Index: 6248912 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.6409. Min Act: -0.1700
Data Index: 7245059 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.6097. Min Act: -0.1700
Data Index: 6250031 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.6097. Min Act: -0.1700
Data Index: 6981002 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5472. Min Act: -0.1700
Data Index: 5174517 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5784. Min Act: -0.1700
Data Index: 7390625 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5472. Min Act: -0.1700
Data Index: 1051216 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5784. Min Act: -0.1700
Data Index: 170983 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5472. Min Act: -0.1700
Data Index: 2323530 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5159. Min Act: -0.1700
Data Index: 1662664 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5472. Min Act: -0.1700
Data Index: 7037211 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.5159. Min Act: -0.1700
Data Index: 6840397 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.4847. Min Act: -0.1700
Data Index: 3339899 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1383137 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4847. Min Range: -6.4847
Max Act: 5.4222. Min Act: -0.1700
Data Index: 342643 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19