Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1339. Min Range: -6.1339
Max Act: 6.1339. Min Act: -0.1700
Data Index: 3798153 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1339. Min Range: -6.1339
Max Act: 6.1026. Min Act: -0.1700
Data Index: 1179329 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1339. Min Range: -6.1339
Max Act: 6.0714. Min Act: -0.1700
Data Index: 7094677 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1339. Min Range: -6.1339
Max Act: 6.0401. Min Act: -0.1700
Data Index: 7817250 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1339. Min Range: -6.1339
Max Act: 6.0401. Min Act: -0.1700
Data Index: 6779601 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9776. Min Act: -0.1700
Data Index: 8480905 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9776. Min Act: -0.1700
Data Index: 7254973 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9776. Min Act: -0.1700
Data Index: 7154499 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9464. Min Act: -0.1700
Data Index: 6833927 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9464. Min Act: -0.1700
Data Index: 1452307 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.9464. Min Act: -0.1700
Data Index: 7762957 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 560321 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8839. Min Act: -0.1699
Data Index: 4560110 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4191089 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 5771417 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8526. Min Act: -0.1700
Data Index: 704320 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1465298 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8839. Min Act: -0.1700
Data Index: 1420155 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8526. Min Act: -0.1700
Data Index: 903610 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1339. Min Range: -6.1339
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1068878 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19