Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.4692. Min Act: -0.1700
Data Index: 7172323 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.2817. Min Act: -0.1700
Data Index: 720302 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.2504. Min Act: -0.1700
Data Index: 4063376 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7179052 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.2192. Min Act: -0.1700
Data Index: 2949903 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.2192. Min Act: -0.1700
Data Index: 5618431 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1879. Min Act: -0.1700
Data Index: 4224815 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1879. Min Act: -0.1700
Data Index: 434111 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1567. Min Act: -0.1700
Data Index: 4621573 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1879. Min Act: -0.1700
Data Index: 5922778 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1567. Min Act: -0.1700
Data Index: 6475187 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1254. Min Act: -0.1700
Data Index: 5614046 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0942. Min Act: -0.1700
Data Index: 7176248 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.1254. Min Act: -0.1700
Data Index: 3055458 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0629. Min Act: -0.1700
Data Index: 2786831 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0942. Min Act: -0.1700
Data Index: 2254157 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0942. Min Act: -0.1700
Data Index: 5851372 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0629. Min Act: -0.1700
Data Index: 3650256 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0629. Min Act: -0.1700
Data Index: 1378578 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4692. Min Range: -5.4692
Max Act: 5.0629. Min Act: -0.1700
Data Index: 6128482 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19