Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5500 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0354. Min Range: -9.0354
Max Act: 9.0354. Min Act: -0.1700
Data Index: 5950905 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0354. Min Range: -9.0354
Max Act: 8.9104. Min Act: -0.1700
Data Index: 1540394 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0354. Min Range: -9.0354
Max Act: 8.2229. Min Act: -0.1700
Data Index: 7149890 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0354. Min Range: -9.0354
Max Act: 8.0979. Min Act: -0.1700
Data Index: 4042367 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0354. Min Range: -9.0354
Max Act: 8.0354. Min Act: -0.1700
Data Index: 8065962 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0354. Min Range: -9.0354
Max Act: 8.0666. Min Act: -0.1700
Data Index: 8316853 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.9416. Min Act: -0.1700
Data Index: 6615292 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.9416. Min Act: -0.1700
Data Index: 87900 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.9104. Min Act: -0.1700
Data Index: 8173118 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.8791. Min Act: -0.1700
Data Index: 2132759 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.8166. Min Act: -0.1700
Data Index: 360668 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.7854. Min Act: -0.1700
Data Index: 5665332 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6916. Min Act: -0.1700
Data Index: 7854675 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6916. Min Act: -0.1700
Data Index: 3904811 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6604. Min Act: -0.1700
Data Index: 5485172 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6604. Min Act: -0.1700
Data Index: 7640476 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6604. Min Act: -0.1700
Data Index: 3004986 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.6291. Min Act: -0.1700
Data Index: 7715413 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.5979. Min Act: -0.1700
Data Index: 517418 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0354. Min Range: -9.0354
Max Act: 7.5666. Min Act: -0.1700
Data Index: 6648146 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19