Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.8080. Min Act: -0.1700
Data Index: 3664368 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.2768. Min Act: -0.1700
Data Index: 6482002 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.1830. Min Act: -0.1700
Data Index: 1626370 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.1518. Min Act: -0.1700
Data Index: 6898240 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.1205. Min Act: -0.1700
Data Index: 5668435 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.1205. Min Act: -0.1700
Data Index: 1152072 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.0893. Min Act: -0.1700
Data Index: 3980144 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.0893. Min Act: -0.1700
Data Index: 8203959 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3566690 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.0268. Min Act: -0.1700
Data Index: 7732215 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9955. Min Act: -0.1700
Data Index: 4066536 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9955. Min Act: -0.1700
Data Index: 5994894 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8080. Min Range: -6.8080
Max Act: 6.0268. Min Act: -0.1700
Data Index: 5135934 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9643. Min Act: -0.1700
Data Index: 2401402 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9955. Min Act: -0.1700
Data Index: 2437002 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9330. Min Act: -0.1700
Data Index: 3364481 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.8705. Min Act: -0.1700
Data Index: 2001567 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.9018. Min Act: -0.1700
Data Index: 2301272 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.8080. Min Act: -0.1700
Data Index: 7425098 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8080. Min Range: -6.8080
Max Act: 5.8080. Min Act: -0.1700
Data Index: 6106196 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19