Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 3232958 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.9666. Min Act: -0.1700
Data Index: 5131854 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.8416. Min Act: -0.1700
Data Index: 2654220 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.7479. Min Act: -0.1700
Data Index: 2654226 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.5916. Min Act: -0.1700
Data Index: 2657465 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.5604. Min Act: -0.1700
Data Index: 7494536 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.5291. Min Act: -0.1700
Data Index: 5627008 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4354. Min Act: -0.1700
Data Index: 2372816 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4666. Min Act: -0.1700
Data Index: 108288 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4354. Min Act: -0.1700
Data Index: 4033451 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4354. Min Act: -0.1700
Data Index: 4514604 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4354. Min Act: -0.1700
Data Index: 3576622 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4041. Min Act: -0.1700
Data Index: 78366 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4041. Min Act: -0.1700
Data Index: 8127779 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4354. Min Act: -0.1700
Data Index: 597540 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.3729. Min Act: -0.1700
Data Index: 2611649 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.4041. Min Act: -0.1700
Data Index: 847199 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.3104. Min Act: -0.1700
Data Index: 7673938 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.3729. Min Act: -0.1700
Data Index: 5074313 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9666. Min Range: -5.9666
Max Act: 5.3416. Min Act: -0.1700
Data Index: 78370 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19