Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.6248. Min Act: -0.1700
Data Index: 654293 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.5623. Min Act: -0.1700
Data Index: 6212846 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.3123. Min Act: -0.1700
Data Index: 101125 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.2186. Min Act: -0.1700
Data Index: 2802805 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1561. Min Act: -0.1700
Data Index: 4461080 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1873. Min Act: -0.1700
Data Index: 6838235 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1873. Min Act: -0.1700
Data Index: 8723593 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1248. Min Act: -0.1700
Data Index: 2504788 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0936. Min Act: -0.1700
Data Index: 2491110 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1248. Min Act: -0.1700
Data Index: 1590312 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1248. Min Act: -0.1700
Data Index: 2634664 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.1248. Min Act: -0.1700
Data Index: 2784902 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0623. Min Act: -0.1700
Data Index: 5759751 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0623. Min Act: -0.1700
Data Index: 742345 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0623. Min Act: -0.1700
Data Index: 7759450 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0623. Min Act: -0.1700
Data Index: 8723599 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6248. Min Range: -8.6248
Max Act: 8.0623. Min Act: -0.1700
Data Index: 8550785 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6248. Min Range: -8.6248
Max Act: 7.9686. Min Act: -0.1700
Data Index: 718517 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6248. Min Range: -8.6248
Max Act: 7.9686. Min Act: -0.1700
Data Index: 464090 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6248. Min Range: -8.6248
Max Act: 7.9686. Min Act: -0.1700
Data Index: 5725742 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19