Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.7798. Min Act: -0.1700
Data Index: 3557801 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.7485. Min Act: -0.1700
Data Index: 8303165 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.7485. Min Act: -0.1700
Data Index: 6434734 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.6548. Min Act: -0.1700
Data Index: 4906588 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.6548. Min Act: -0.1700
Data Index: 8606188 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.6235. Min Act: -0.1700
Data Index: 1350279 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.5610. Min Act: -0.1700
Data Index: 4820992 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.5610. Min Act: -0.1700
Data Index: 7627396 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.5610. Min Act: -0.1700
Data Index: 135241 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.5610. Min Act: -0.1700
Data Index: 7877525 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4673. Min Act: -0.1700
Data Index: 446608 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4673. Min Act: -0.1700
Data Index: 795612 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4985. Min Act: -0.1700
Data Index: 3802913 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4360. Min Act: -0.1700
Data Index: 4807330 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4048. Min Act: -0.1700
Data Index: 2241755 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4360. Min Act: -0.1700
Data Index: 1275926 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.4360. Min Act: -0.1700
Data Index: 6062509 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.3735. Min Act: -0.1700
Data Index: 6593598 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.3735. Min Act: -0.1700
Data Index: 3664849 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7798. Min Range: -7.7798
Max Act: 7.3735. Min Act: -0.1700
Data Index: 3715993 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19