Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.3468. Min Act: -0.1700
Data Index: 1901488 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.3468. Min Act: -0.1700
Data Index: 7652772 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.1593. Min Act: -0.1700
Data Index: 29406 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.1281. Min Act: -0.1700
Data Index: 2485209 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.1281. Min Act: -0.1700
Data Index: 4004092 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0968. Min Act: -0.1700
Data Index: 4040351 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0656. Min Act: -0.1700
Data Index: 1753880 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0343. Min Act: -0.1700
Data Index: 6246220 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0343. Min Act: -0.1700
Data Index: 1197150 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0343. Min Act: -0.1700
Data Index: 3426985 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0343. Min Act: -0.1700
Data Index: 4465625 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0031. Min Act: -0.1700
Data Index: 5637542 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0031. Min Act: -0.1700
Data Index: 1389231 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0031. Min Act: -0.1700
Data Index: 8367266 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0031. Min Act: -0.1700
Data Index: 3947259 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3468. Min Range: -6.3468
Max Act: 6.0343. Min Act: -0.1700
Data Index: 7899724 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3468. Min Range: -6.3468
Max Act: 5.9718. Min Act: -0.1700
Data Index: 3111718 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3468. Min Range: -6.3468
Max Act: 5.9718. Min Act: -0.1700
Data Index: 6810643 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3468. Min Range: -6.3468
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1888016 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3468. Min Range: -6.3468
Max Act: 5.9718. Min Act: -0.1700
Data Index: 5702633 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19