Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.7393. Min Act: -0.1700
Data Index: 2165500 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.2393. Min Act: -0.1700
Data Index: 3049168 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.1455. Min Act: -0.1700
Data Index: 6314030 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.1143. Min Act: -0.1700
Data Index: 7142920 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.0518. Min Act: -0.1700
Data Index: 1740604 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7393. Min Range: -6.7393
Max Act: 6.0205. Min Act: -0.1700
Data Index: 1331353 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.9893. Min Act: -0.1700
Data Index: 292157 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.9893. Min Act: -0.1700
Data Index: 5655252 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.9893. Min Act: -0.1700
Data Index: 3228691 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.9893. Min Act: -0.1700
Data Index: 2552695 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.9893. Min Act: -0.1700
Data Index: 3322357 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8955. Min Act: -0.1700
Data Index: 1298444 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8955. Min Act: -0.1700
Data Index: 4587954 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8955. Min Act: -0.1700
Data Index: 3411722 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8643. Min Act: -0.1700
Data Index: 101698 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8955. Min Act: -0.1700
Data Index: 2549968 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8643. Min Act: -0.1700
Data Index: 727588 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8643. Min Act: -0.1700
Data Index: 3189924 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8330. Min Act: -0.1700
Data Index: 1173841 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7393. Min Range: -6.7393
Max Act: 5.8330. Min Act: -0.1700
Data Index: 5337233 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19