Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3873 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.2245. Min Act: -0.1700
Data Index: 3977820 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.1144. Min Act: -0.1700
Data Index: 7866004 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.0197. Min Act: -0.1700
Data Index: 7217322 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.0197. Min Act: -0.1700
Data Index: 3839470 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.0039. Min Act: -0.1700
Data Index: 3493503 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2245. Min Range: -3.2245
Max Act: 3.0197. Min Act: -0.1700
Data Index: 1164268 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.9723. Min Act: -0.1700
Data Index: 7998152 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.9723. Min Act: -0.1700
Data Index: 8030028 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.9090. Min Act: -0.1700
Data Index: 4186492 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.9248. Min Act: -0.1700
Data Index: 7136148 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8931. Min Act: -0.1700
Data Index: 5175561 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.9090. Min Act: -0.1700
Data Index: 4096727 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8931. Min Act: -0.1700
Data Index: 2132539 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8772. Min Act: -0.1700
Data Index: 3002906 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8614. Min Act: -0.1700
Data Index: 707756 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8772. Min Act: -0.1700
Data Index: 3355133 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8931. Min Act: -0.1700
Data Index: 1380593 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8614. Min Act: -0.1700
Data Index: 7729421 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8614. Min Act: -0.1700
Data Index: 7190871 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2245. Min Range: -3.2245
Max Act: 2.8614. Min Act: -0.1700
Data Index: 3898259 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19