Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.3613. Min Act: -0.1700
Data Index: 3034797 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.2363. Min Act: -0.1700
Data Index: 4699246 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.2363. Min Act: -0.1700
Data Index: 2506231 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.2050. Min Act: -0.1700
Data Index: 538657 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.2363. Min Act: -0.1700
Data Index: 6145527 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.1738. Min Act: -0.1700
Data Index: 3892509 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.1113. Min Act: -0.1700
Data Index: 8521790 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0175. Min Act: -0.1700
Data Index: 550157 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0488. Min Act: -0.1700
Data Index: 4430245 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0488. Min Act: -0.1700
Data Index: 2105386 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0175. Min Act: -0.1700
Data Index: 3849142 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0175. Min Act: -0.1700
Data Index: 61011 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9863. Min Act: -0.1700
Data Index: 7973855 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9863. Min Act: -0.1700
Data Index: 1540210 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5095693 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3613. Min Range: -5.3613
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4588255 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9550. Min Act: -0.1700
Data Index: 8139415 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9863. Min Act: -0.1700
Data Index: 2056162 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5882956 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3613. Min Range: -5.3613
Max Act: 4.9550. Min Act: -0.1700
Data Index: 2350418 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19