Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 674 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.3406. Min Act: -0.1700
Data Index: 6477400 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.2468. Min Act: -0.1700
Data Index: 5265783 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.2156. Min Act: -0.1700
Data Index: 666461 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.2156. Min Act: -0.1700
Data Index: 2157659 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.2156. Min Act: -0.1700
Data Index: 6802241 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.2156. Min Act: -0.1700
Data Index: 851242 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1843. Min Act: -0.1700
Data Index: 8470630 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1531. Min Act: -0.1700
Data Index: 4442686 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1531. Min Act: -0.1700
Data Index: 5839114 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1218. Min Act: -0.1700
Data Index: 5860690 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3659102 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1531. Min Act: -0.1700
Data Index: 888600 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1218. Min Act: -0.1700
Data Index: 7273416 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0906. Min Act: -0.1700
Data Index: 1178318 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.1531. Min Act: -0.1700
Data Index: 7395512 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0906. Min Act: -0.1699
Data Index: 5974398 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0906. Min Act: -0.1700
Data Index: 6204038 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0593. Min Act: -0.1700
Data Index: 6240517 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0906. Min Act: -0.1699
Data Index: 4985100 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3406. Min Range: -5.3406
Max Act: 5.0281. Min Act: -0.1700
Data Index: 1010373 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19