Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2088. Min Range: -9.2088
Max Act: 9.2088. Min Act: -0.1700
Data Index: 270652 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.9588. Min Act: -0.1700
Data Index: 720290 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.4588. Min Act: -0.1700
Data Index: 5801343 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.4588. Min Act: -0.1700
Data Index: 4476127 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.5213. Min Act: -0.1700
Data Index: 7897018 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3963. Min Act: -0.1700
Data Index: 2135455 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3963. Min Act: -0.1700
Data Index: 7770228 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3963. Min Act: -0.1700
Data Index: 2644639 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3338. Min Act: -0.1700
Data Index: 7989703 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3338. Min Act: -0.1700
Data Index: 5950557 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3338. Min Act: -0.1700
Data Index: 7305090 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3338. Min Act: -0.1700
Data Index: 5028703 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.2713. Min Act: -0.1700
Data Index: 2625700 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.3338. Min Act: -0.1700
Data Index: 7328447 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.2088. Min Act: -0.1700
Data Index: 6049189 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.2088. Min Act: -0.1700
Data Index: 8348721 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.2088. Min Act: -0.1700
Data Index: 7929335 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.2088. Min Act: -0.1700
Data Index: 3111488 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.1463. Min Act: -0.1700
Data Index: 808587 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2088. Min Range: -9.2088
Max Act: 8.1463. Min Act: -0.1700
Data Index: 7688116 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19