Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.7534. Min Act: -0.1700
Data Index: 5598478 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.6284. Min Act: -0.1700
Data Index: 7879163 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.5034. Min Act: -0.1700
Data Index: 483098 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.5034. Min Act: -0.1700
Data Index: 318289 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.3784. Min Act: -0.1700
Data Index: 3638200 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.3784. Min Act: -0.1700
Data Index: 663748 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.3784. Min Act: -0.1700
Data Index: 4840397 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.3784. Min Act: -0.1700
Data Index: 2773873 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.3159. Min Act: -0.1700
Data Index: 7152892 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.2534. Min Act: -0.1700
Data Index: 1525125 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.2534. Min Act: -0.1700
Data Index: 6015079 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.2534. Min Act: -0.1700
Data Index: 8757807 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.2534. Min Act: -0.1700
Data Index: 1712030 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.2534. Min Act: -0.1700
Data Index: 1056612 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 6174266 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 4629223 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 8613086 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 4092455 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 6625923 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7534. Min Range: -10.7534
Max Act: 10.1909. Min Act: -0.1700
Data Index: 7801411 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19