Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.7676. Min Act: -0.1700
Data Index: 2814125 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 8775858 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6114. Min Act: -0.1700
Data Index: 5721777 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 8087701 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4239. Min Act: -0.1700
Data Index: 2971875 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 6910454 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3926. Min Act: -0.1700
Data Index: 2096235 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3614. Min Act: -0.1700
Data Index: 1098965 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3301. Min Act: -0.1700
Data Index: 4018150 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4375658 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3301. Min Act: -0.1700
Data Index: 6517206 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2989. Min Act: -0.1700
Data Index: 5671832 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2676. Min Act: -0.1700
Data Index: 4901466 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2676. Min Act: -0.1700
Data Index: 5979250 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2364. Min Act: -0.1700
Data Index: 2660991 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2364. Min Act: -0.1700
Data Index: 1985622 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2051. Min Act: -0.1700
Data Index: 33605 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2364. Min Act: -0.1700
Data Index: 1335012 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2364. Min Act: -0.1700
Data Index: 2826241 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.2364. Min Act: -0.1700
Data Index: 5864458 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19