Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.8517. Min Act: -0.1700
Data Index: 4209759 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.8204. Min Act: -0.1700
Data Index: 4364359 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.6017. Min Act: -0.1700
Data Index: 4156161 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.5392. Min Act: -0.1700
Data Index: 2604946 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.5079. Min Act: -0.1700
Data Index: 2561032 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.5079. Min Act: -0.1700
Data Index: 1963731 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.5079. Min Act: -0.1700
Data Index: 1889154 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.4767. Min Act: -0.1700
Data Index: 4800470 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.4454. Min Act: -0.1700
Data Index: 2604945 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.4454. Min Act: -0.1700
Data Index: 4722500 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.4142. Min Act: -0.1700
Data Index: 1472398 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.3517. Min Act: -0.1700
Data Index: 2561031 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.3204. Min Act: -0.1700
Data Index: 4632606 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.3204. Min Act: -0.1700
Data Index: 3719595 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2579. Min Act: -0.1700
Data Index: 7526666 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2579. Min Act: -0.1700
Data Index: 1096814 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2892. Min Act: -0.1700
Data Index: 3204264 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2579. Min Act: -0.1700
Data Index: 156308 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2579. Min Act: -0.1700
Data Index: 6188994 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8517. Min Range: -6.8517
Max Act: 6.2267. Min Act: -0.1700
Data Index: 12150 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19