Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 8006565 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.3872. Min Act: -0.1700
Data Index: 2770458 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.3872. Min Act: -0.1700
Data Index: 2794296 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 5711000 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.3872. Min Act: -0.1700
Data Index: 2402105 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.2309. Min Act: -0.1700
Data Index: 3961952 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.2622. Min Act: -0.1700
Data Index: 8326259 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.2309. Min Act: -0.1700
Data Index: 7122114 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1997. Min Act: -0.1700
Data Index: 227263 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 7777638 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 3988643 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 7883483 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 7445726 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 3328445 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1372. Min Act: -0.1700
Data Index: 804941 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1684. Min Act: -0.1700
Data Index: 6633774 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1372. Min Act: -0.1700
Data Index: 1768528 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1372. Min Act: -0.1700
Data Index: 3961951 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1059. Min Act: -0.1700
Data Index: 4406626 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4809. Min Range: -7.4809
Max Act: 7.1059. Min Act: -0.1700
Data Index: 5864602 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19