Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0034. Min Range: -6.0034
Max Act: 6.0034. Min Act: -0.1700
Data Index: 4949799 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.8472. Min Act: -0.1700
Data Index: 3669395 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.7534. Min Act: -0.1700
Data Index: 6532541 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.6597. Min Act: -0.1700
Data Index: 1695737 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.6597. Min Act: -0.1700
Data Index: 6015531 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5972. Min Act: -0.1700
Data Index: 867397 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5659. Min Act: -0.1700
Data Index: 7733615 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5659. Min Act: -0.1700
Data Index: 1228544 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5347. Min Act: -0.1700
Data Index: 431080 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5034. Min Act: -0.1700
Data Index: 6624595 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.5034. Min Act: -0.1700
Data Index: 681164 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4722. Min Act: -0.1700
Data Index: 2299093 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4409. Min Act: -0.1700
Data Index: 6188943 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4722. Min Act: -0.1700
Data Index: 5125470 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4409. Min Act: -0.1700
Data Index: 1053988 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4097. Min Act: -0.1700
Data Index: 8411226 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4097. Min Act: -0.1700
Data Index: 7247519 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4097. Min Act: -0.1700
Data Index: 5449485 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4097. Min Act: -0.1700
Data Index: 2249057 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0034. Min Range: -6.0034
Max Act: 5.4097. Min Act: -0.1700
Data Index: 861652 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19