Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.6406. Min Act: -0.1700
Data Index: 4652848 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.5781. Min Act: -0.1700
Data Index: 3550002 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.5781. Min Act: -0.1700
Data Index: 3955046 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.4531. Min Act: -0.1700
Data Index: 6519318 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.4219. Min Act: -0.1700
Data Index: 5733341 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.4219. Min Act: -0.1700
Data Index: 180546 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.4531. Min Act: -0.1700
Data Index: 6507582 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.4219. Min Act: -0.1700
Data Index: 7524364 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2969. Min Act: -0.1700
Data Index: 2926798 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2969. Min Act: -0.1700
Data Index: 1418089 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2656. Min Act: -0.1700
Data Index: 5943762 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2656. Min Act: -0.1700
Data Index: 7812419 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2656. Min Act: -0.1700
Data Index: 3090991 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2344. Min Act: -0.1700
Data Index: 6678290 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2656. Min Act: -0.1700
Data Index: 8514733 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2344. Min Act: -0.1700
Data Index: 5987203 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2031. Min Act: -0.1700
Data Index: 3096755 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2344. Min Act: -0.1700
Data Index: 8777285 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2031. Min Act: -0.1700
Data Index: 1044920 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6406. Min Range: -7.6406
Max Act: 7.2344. Min Act: -0.1700
Data Index: 5788089 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19