Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1190 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2490. Min Range: -7.2490
Max Act: 7.2490. Min Act: -0.1700
Data Index: 3033553 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2490. Min Range: -7.2490
Max Act: 7.0615. Min Act: -0.1700
Data Index: 5274741 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2490. Min Range: -7.2490
Max Act: 7.0615. Min Act: -0.1700
Data Index: 3887240 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2490. Min Range: -7.2490
Max Act: 7.0302. Min Act: -0.1700
Data Index: 2937170 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.9990. Min Act: -0.1700
Data Index: 4038582 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.9052. Min Act: -0.1700
Data Index: 137394 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4732029 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8427. Min Act: -0.1700
Data Index: 1832315 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8115. Min Act: -0.1700
Data Index: 4038567 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.8115. Min Act: -0.1700
Data Index: 4086226 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7802. Min Act: -0.1700
Data Index: 2281657 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7490. Min Act: -0.1700
Data Index: 1769331 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7177. Min Act: -0.1700
Data Index: 3398446 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7177. Min Act: -0.1700
Data Index: 1747419 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7177. Min Act: -0.1700
Data Index: 5620794 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.7177. Min Act: -0.1700
Data Index: 6668074 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6865. Min Act: -0.1700
Data Index: 891667 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6865. Min Act: -0.1700
Data Index: 2267438 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6961110 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2490. Min Range: -7.2490
Max Act: 6.6865. Min Act: -0.1700
Data Index: 1575850 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19