Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.8738. Min Act: -0.1700
Data Index: 6460484 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.9050. Min Act: -0.1700
Data Index: 6077598 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.8738. Min Act: -0.1700
Data Index: 3569835 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.7800. Min Act: -0.1700
Data Index: 4259702 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.6550. Min Act: -0.1700
Data Index: 3000991 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.5925. Min Act: -0.1700
Data Index: 8732161 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.6863. Min Act: -0.1700
Data Index: 5507284 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.5613. Min Act: -0.1700
Data Index: 4435605 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.5300. Min Act: -0.1700
Data Index: 7824545 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.4675. Min Act: -0.1700
Data Index: 281532 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.5300. Min Act: -0.1700
Data Index: 1658334 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.4363. Min Act: -0.1700
Data Index: 6271005 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.4050. Min Act: -0.1700
Data Index: 2786166 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.4050. Min Act: -0.1700
Data Index: 3195406 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.3425. Min Act: -0.1700
Data Index: 2979870 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.3738. Min Act: -0.1700
Data Index: 968764 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.3425. Min Act: -0.1700
Data Index: 3114076 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.4363. Min Act: -0.1700
Data Index: 7043318 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.3113. Min Act: -0.1700
Data Index: 4663176 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9050. Min Range: -7.9050
Max Act: 7.3113. Min Act: -0.1700
Data Index: 7612202 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19