Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.9815. Min Act: -0.1700
Data Index: 6502720 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.9190. Min Act: -0.1700
Data Index: 11394 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.7315. Min Act: -0.1700
Data Index: 1476539 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.7315. Min Act: -0.1700
Data Index: 3679084 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.7315. Min Act: -0.1700
Data Index: 3846491 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.6690. Min Act: -0.1700
Data Index: 5999761 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.6065. Min Act: -0.1700
Data Index: 6957089 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.6065. Min Act: -0.1700
Data Index: 3771194 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.6065. Min Act: -0.1700
Data Index: 399468 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.5753. Min Act: -0.1700
Data Index: 983376 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.5128. Min Act: -0.1700
Data Index: 6404843 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2962589 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.5128. Min Act: -0.1700
Data Index: 5181206 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4815. Min Act: -0.1700
Data Index: 3406151 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.5128. Min Act: -0.1700
Data Index: 5499721 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4503. Min Act: -0.1700
Data Index: 8224997 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4503. Min Act: -0.1700
Data Index: 4523953 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4503. Min Act: -0.1700
Data Index: 8629333 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4190. Min Act: -0.1700
Data Index: 1377216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9815. Min Range: -7.9815
Max Act: 7.4503. Min Act: -0.1700
Data Index: 871198 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19