Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7603. Min Range: -7.7603
Max Act: 7.7603. Min Act: -0.1700
Data Index: 7476476 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1696433 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.9791. Min Act: -0.1700
Data Index: 553742 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7603. Min Range: -7.7603
Max Act: 7.0416. Min Act: -0.1700
Data Index: 1629716 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7603. Min Range: -7.7603
Max Act: 7.2291. Min Act: -0.1700
Data Index: 825681 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.3541. Min Act: -0.1700
Data Index: 7008623 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.8228. Min Act: -0.1700
Data Index: 2743695 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.3853. Min Act: -0.1700
Data Index: 7107556 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.0103. Min Act: -0.1700
Data Index: 1760091 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.6666. Min Act: -0.1700
Data Index: 5362809 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7603. Min Range: -7.7603
Max Act: 5.9478. Min Act: -0.1700
Data Index: 1107231 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3207940 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.5416. Min Act: -0.1700
Data Index: 2928794 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.3853. Min Act: -0.1700
Data Index: 2298080 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.0103. Min Act: -0.1700
Data Index: 1043455 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.0103. Min Act: -0.1700
Data Index: 2653281 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.3853. Min Act: -0.1700
Data Index: 561046 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.8541. Min Act: -0.1700
Data Index: 8193990 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.5728. Min Act: -0.1700
Data Index: 2663599 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7603. Min Range: -7.7603
Max Act: 6.5103. Min Act: -0.1700
Data Index: 4130684 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19