Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.9592. Min Act: -0.1700
Data Index: 1092448 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.8342. Min Act: -0.1700
Data Index: 913813 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.7092. Min Act: -0.1700
Data Index: 2145771 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.6467. Min Act: -0.1700
Data Index: 470438 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.5842. Min Act: -0.1700
Data Index: 2478141 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.5842. Min Act: -0.1700
Data Index: 2741110 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.5217. Min Act: -0.1700
Data Index: 8134895 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.4279. Min Act: -0.1700
Data Index: 4570195 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3967. Min Act: -0.1700
Data Index: 7036315 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3654. Min Act: -0.1700
Data Index: 1900300 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3654. Min Act: -0.1700
Data Index: 7925661 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3654. Min Act: -0.1700
Data Index: 392832 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3654. Min Act: -0.1700
Data Index: 1852206 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3654. Min Act: -0.1700
Data Index: 6702570 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3342. Min Act: -0.1700
Data Index: 418236 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.2717. Min Act: -0.1700
Data Index: 5335462 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.2717. Min Act: -0.1700
Data Index: 371972 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.2717. Min Act: -0.1700
Data Index: 5435490 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3029. Min Act: -0.1700
Data Index: 1056054 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9592. Min Range: -7.9592
Max Act: 7.3029. Min Act: -0.1700
Data Index: 4315616 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19