Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1447. Min Range: -6.1447
Max Act: 6.1447. Min Act: -0.1700
Data Index: 3225371 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.9572. Min Act: -0.1700
Data Index: 5325051 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.8322. Min Act: -0.1700
Data Index: 8799537 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.8322. Min Act: -0.1700
Data Index: 6900119 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.8322. Min Act: -0.1700
Data Index: 8443689 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.7697. Min Act: -0.1700
Data Index: 2018046 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.7384. Min Act: -0.1700
Data Index: 5704197 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6759. Min Act: -0.1700
Data Index: 1142040 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 3449220 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 1197241 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 7868816 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 20446 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6447. Min Act: -0.1700
Data Index: 262534 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6134. Min Act: -0.1700
Data Index: 5755636 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.6134. Min Act: -0.1700
Data Index: 5126084 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.5509. Min Act: -0.1700
Data Index: 1459845 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6628212 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6743749 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.5509. Min Act: -0.1700
Data Index: 7822118 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1447. Min Range: -6.1447
Max Act: 5.5509. Min Act: -0.1700
Data Index: 590773 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19