Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1647 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2979. Min Range: -6.2979
Max Act: 6.2979. Min Act: -0.1700
Data Index: 5270882 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2953237 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.9854. Min Act: -0.1700
Data Index: 1903261 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.9229. Min Act: -0.1700
Data Index: 908259 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3035974 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3819434 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7666. Min Act: -0.1700
Data Index: 6422249 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4906361 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7354. Min Act: -0.1700
Data Index: 417004 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7354. Min Act: -0.1700
Data Index: 5031419 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7666. Min Act: -0.1700
Data Index: 1511617 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7354. Min Act: -0.1700
Data Index: 6578934 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7384052 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7807207 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6729. Min Act: -0.1700
Data Index: 596898 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6729. Min Act: -0.1700
Data Index: 1979574 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6416. Min Act: -0.1700
Data Index: 6958600 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6416. Min Act: -0.1700
Data Index: 7657466 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8015104 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2979. Min Range: -6.2979
Max Act: 5.6416. Min Act: -0.1700
Data Index: 2679622 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19