Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.5025. Min Act: -0.1700
Data Index: 8517031 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.3775. Min Act: -0.1700
Data Index: 3504696 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.1900. Min Act: -0.1700
Data Index: 8109242 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.1900. Min Act: -0.1700
Data Index: 5786161 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.1275. Min Act: -0.1700
Data Index: 1752480 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.1275. Min Act: -0.1700
Data Index: 969686 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.0025. Min Act: -0.1700
Data Index: 8134939 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5025. Min Range: -8.5025
Max Act: 8.0025. Min Act: -0.1700
Data Index: 932105 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.9400. Min Act: -0.1700
Data Index: 4581491 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.9400. Min Act: -0.1700
Data Index: 6063141 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.8775. Min Act: -0.1700
Data Index: 5645541 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.8150. Min Act: -0.1700
Data Index: 3034742 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.8150. Min Act: -0.1700
Data Index: 2583247 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.8150. Min Act: -0.1700
Data Index: 4146260 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.8150. Min Act: -0.1700
Data Index: 6408894 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.7525. Min Act: -0.1700
Data Index: 5253541 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.6900. Min Act: -0.1700
Data Index: 8142418 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.6900. Min Act: -0.1700
Data Index: 4642257 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.7525. Min Act: -0.1700
Data Index: 409734 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5025. Min Range: -8.5025
Max Act: 7.6275. Min Act: -0.1700
Data Index: 3635136 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19