Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5627 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.6252. Min Act: -0.1700
Data Index: 6393608 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.5627. Min Act: -0.1700
Data Index: 3624417 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.4065. Min Act: -0.1700
Data Index: 3624419 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.3752. Min Act: -0.1700
Data Index: 6393607 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.2190. Min Act: -0.1700
Data Index: 6393609 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6252. Min Range: -7.6252
Max Act: 7.0002. Min Act: -0.1700
Data Index: 1253844 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.9377. Min Act: -0.1700
Data Index: 7535353 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.9377. Min Act: -0.1700
Data Index: 6902986 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.9377. Min Act: -0.1700
Data Index: 2922681 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7815. Min Act: -0.1700
Data Index: 3624418 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7815. Min Act: -0.1700
Data Index: 2175778 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7815. Min Act: -0.1700
Data Index: 109168 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7502. Min Act: -0.1700
Data Index: 1397508 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7190. Min Act: -0.1700
Data Index: 4640632 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7190. Min Act: -0.1700
Data Index: 7709003 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.7190. Min Act: -0.1700
Data Index: 169718 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.6877. Min Act: -0.1700
Data Index: 7535354 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.6877. Min Act: -0.1700
Data Index: 6902985 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.6565. Min Act: -0.1700
Data Index: 5860453 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6252. Min Range: -7.6252
Max Act: 6.6565. Min Act: -0.1700
Data Index: 3624416 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19