Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.5066. Min Act: -0.1700
Data Index: 6286295 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.3816. Min Act: -0.1700
Data Index: 301797 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.3190. Min Act: -0.1700
Data Index: 7691937 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.2253. Min Act: -0.1700
Data Index: 2524076 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1628. Min Act: -0.1700
Data Index: 1464989 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1003. Min Act: -0.1700
Data Index: 7958351 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1315. Min Act: -0.1700
Data Index: 7001140 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1315. Min Act: -0.1700
Data Index: 3831389 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1315. Min Act: -0.1700
Data Index: 6561630 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1003. Min Act: -0.1700
Data Index: 6569677 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0690. Min Act: -0.1700
Data Index: 4747051 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.1003. Min Act: -0.1700
Data Index: 2358476 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0378. Min Act: -0.1700
Data Index: 2081325 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0690. Min Act: -0.1700
Data Index: 1911019 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0378. Min Act: -0.1700
Data Index: 6169078 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0378. Min Act: -0.1700
Data Index: 1346718 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0065. Min Act: -0.1700
Data Index: 4651550 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5066. Min Range: -4.5066
Max Act: 4.0378. Min Act: -0.1700
Data Index: 3949286 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5066. Min Range: -4.5066
Max Act: 3.9752. Min Act: -0.1700
Data Index: 3015127 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5066. Min Range: -4.5066
Max Act: 3.9440. Min Act: -0.1700
Data Index: 3865587 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19