Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1177 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0920. Min Range: -8.0920
Max Act: 8.0920. Min Act: -0.1700
Data Index: 7884585 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.7170. Min Act: -0.1700
Data Index: 7475343 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.6545. Min Act: -0.1700
Data Index: 5186791 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5920. Min Act: -0.1700
Data Index: 5544074 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5295. Min Act: -0.1700
Data Index: 7381985 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5295. Min Act: -0.1700
Data Index: 1101867 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5295. Min Act: -0.1700
Data Index: 2439278 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5295. Min Act: -0.1700
Data Index: 7694664 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.5295. Min Act: -0.1700
Data Index: 8815705 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4983. Min Act: -0.1700
Data Index: 8626826 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4983. Min Act: -0.1700
Data Index: 6432993 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4983. Min Act: -0.1700
Data Index: 8280587 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 410243 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 5544075 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 3407406 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 4847927 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 4703625 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4670. Min Act: -0.1700
Data Index: 8209860 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4358. Min Act: -0.1700
Data Index: 8189329 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0920. Min Range: -8.0920
Max Act: 7.4358. Min Act: -0.1699
Data Index: 1833129 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19