Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5328 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.4365. Min Act: -0.1700
Data Index: 1138310 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.2178. Min Act: -0.1700
Data Index: 5447231 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.2178. Min Act: -0.1700
Data Index: 7383648 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.1553. Min Act: -0.1700
Data Index: 1523321 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0928. Min Act: -0.1700
Data Index: 3663812 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0928. Min Act: -0.1700
Data Index: 7040836 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.1240. Min Act: -0.1700
Data Index: 4488040 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0928. Min Act: -0.1700
Data Index: 6317080 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0615. Min Act: -0.1700
Data Index: 4458601 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0615. Min Act: -0.1698
Data Index: 8578388 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0303. Min Act: -0.1700
Data Index: 1609583 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0303. Min Act: -0.1700
Data Index: 4830139 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0303. Min Act: -0.1700
Data Index: 5787222 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4365. Min Range: -6.4365
Max Act: 6.0303. Min Act: -0.1700
Data Index: 6912320 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9990. Min Act: -0.1700
Data Index: 656542 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9990. Min Act: -0.1700
Data Index: 1633805 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9678. Min Act: -0.1700
Data Index: 433745 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9990. Min Act: -0.1700
Data Index: 7827177 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9678. Min Act: -0.1700
Data Index: 3867531 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4365. Min Range: -6.4365
Max Act: 5.9678. Min Act: -0.1700
Data Index: 7258545 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19