Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.9214. Min Act: -0.1700
Data Index: 4116525 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.8589. Min Act: -0.1700
Data Index: 4226931 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7964. Min Act: -0.1700
Data Index: 3043513 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 8077142 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 139904 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 3938926 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 1178831 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 8292377 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 6638697 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 4106732 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 1308930 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 1103300 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 1706044 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 1776079 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 4831347 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 857345 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 3154990 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 6392800 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 6479927 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9214. Min Range: -7.9214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 3265758 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19