Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6345 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 939075 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 3619370 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3203. Min Act: -0.1700
Data Index: 8483562 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2890. Min Act: -0.1700
Data Index: 478106 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2578. Min Act: -0.1700
Data Index: 987629 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2265. Min Act: -0.1700
Data Index: 3233098 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1640. Min Act: -0.1700
Data Index: 1515738 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1328. Min Act: -0.1700
Data Index: 2843319 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 2438228 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0703. Min Act: -0.1700
Data Index: 8518748 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0703. Min Act: -0.1700
Data Index: 347796 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0703. Min Act: -0.1700
Data Index: 497450 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 7628676 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2981395 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2351556 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 5618516 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9453. Min Act: -0.1700
Data Index: 921634 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9140. Min Act: -0.1700
Data Index: 8171821 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8515. Min Act: -0.1700
Data Index: 2334095 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8515. Min Act: -0.1700
Data Index: 2376285 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19