Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6225 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.5123. Min Act: -0.1700
Data Index: 1381262 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.4498. Min Act: -0.1700
Data Index: 5039206 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.2623. Min Act: -0.1700
Data Index: 3252725 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.0436. Min Act: -0.1700
Data Index: 2905856 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.0123. Min Act: -0.1700
Data Index: 5100893 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5123. Min Range: -8.5123
Max Act: 8.0123. Min Act: -0.1700
Data Index: 7550938 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.9811. Min Act: -0.1700
Data Index: 383355 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.9498. Min Act: -0.1700
Data Index: 6093980 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.9186. Min Act: -0.1700
Data Index: 8041877 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.9186. Min Act: -0.1700
Data Index: 8372761 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.8873. Min Act: -0.1700
Data Index: 3831929 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.8561. Min Act: -0.1700
Data Index: 6869322 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.8248. Min Act: -0.1700
Data Index: 3355397 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.8248. Min Act: -0.1700
Data Index: 5687306 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.7623. Min Act: -0.1700
Data Index: 7495213 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.7311. Min Act: -0.1700
Data Index: 2376989 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.6998. Min Act: -0.1700
Data Index: 1343498 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.6998. Min Act: -0.1700
Data Index: 8044243 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.6373. Min Act: -0.1700
Data Index: 6538873 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5123. Min Range: -8.5123
Max Act: 7.6686. Min Act: -0.1700
Data Index: 1776920 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19