Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.8918. Min Act: -0.1700
Data Index: 1662187 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.8293. Min Act: -0.1700
Data Index: 1071597 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.6418. Min Act: -0.1700
Data Index: 6090554 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.7043. Min Act: -0.1700
Data Index: 6814126 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.7043. Min Act: -0.1700
Data Index: 6060319 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.5793. Min Act: -0.1700
Data Index: 5860398 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.5168. Min Act: -0.1700
Data Index: 5514453 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.4543. Min Act: -0.1700
Data Index: 4111172 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.4543. Min Act: -0.1700
Data Index: 7050994 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.3918. Min Act: -0.1700
Data Index: 5255914 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.3918. Min Act: -0.1700
Data Index: 3203351 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.3293. Min Act: -0.1700
Data Index: 1721858 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.3293. Min Act: -0.1700
Data Index: 514174 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2668. Min Act: -0.1700
Data Index: 7648920 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2668. Min Act: -0.1700
Data Index: 4509680 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2043. Min Act: -0.1700
Data Index: 7554703 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2043. Min Act: -0.1700
Data Index: 6187496 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2043. Min Act: -0.1700
Data Index: 6199280 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2043. Min Act: -0.1700
Data Index: 6397458 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8918. Min Range: -9.8918
Max Act: 9.2043. Min Act: -0.1700
Data Index: 1795770 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19