Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.7610. Min Act: -0.1700
Data Index: 1518185 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.7141. Min Act: -0.1699
Data Index: 1501791 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.6515. Min Act: -0.1700
Data Index: 3126613 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.6358. Min Act: -0.1700
Data Index: 2676212 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.6045. Min Act: -0.1700
Data Index: 8065761 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.6045. Min Act: -0.1700
Data Index: 200523 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.5419. Min Act: -0.1699
Data Index: 6313295 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.5106. Min Act: -0.1700
Data Index: 8309819 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4949. Min Act: -0.1700
Data Index: 6100100 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4793. Min Act: -0.1700
Data Index: 8482619 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4793. Min Act: -0.1700
Data Index: 3324613 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4793. Min Act: -0.1700
Data Index: 1737753 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4636. Min Act: -0.1700
Data Index: 697371 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4793. Min Act: -0.1700
Data Index: 5440632 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4636. Min Act: -0.1700
Data Index: 5752839 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4479. Min Act: -0.1700
Data Index: 3692636 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4636. Min Act: -0.1700
Data Index: 5374476 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4166. Min Act: -0.1700
Data Index: 327243 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4323. Min Act: -0.1700
Data Index: 2775462 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7610. Min Range: -3.7610
Max Act: 3.4323. Min Act: -0.1700
Data Index: 4842993 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19