Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1345 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.6839. Min Act: -0.1700
Data Index: 2425773 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.5276. Min Act: -0.1700
Data Index: 5022877 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.4651. Min Act: -0.1700
Data Index: 3210785 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.4964. Min Act: -0.1700
Data Index: 8355062 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.4339. Min Act: -0.1700
Data Index: 7273432 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.4026. Min Act: -0.1700
Data Index: 4579794 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3401. Min Act: -0.1700
Data Index: 3664284 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3714. Min Act: -0.1700
Data Index: 487003 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3714. Min Act: -0.1700
Data Index: 504943 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3714. Min Act: -0.1700
Data Index: 6856949 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3401. Min Act: -0.1700
Data Index: 8386885 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3714. Min Act: -0.1700
Data Index: 6133507 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3089. Min Act: -0.1700
Data Index: 3949408 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.2776. Min Act: -0.1700
Data Index: 3527159 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.3089. Min Act: -0.1700
Data Index: 3825333 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.2464. Min Act: -0.1700
Data Index: 5627643 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.2464. Min Act: -0.1700
Data Index: 1812502 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.1839. Min Act: -0.1700
Data Index: 844594 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.1839. Min Act: -0.1700
Data Index: 8361362 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6839. Min Range: -5.6839
Max Act: 5.1214. Min Act: -0.1700
Data Index: 6342261 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19