Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.6300. Min Act: -0.1700
Data Index: 6746144 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.3800. Min Act: -0.1700
Data Index: 520283 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.3488. Min Act: -0.1700
Data Index: 1267528 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.2550. Min Act: -0.1700
Data Index: 9773 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.2550. Min Act: -0.1700
Data Index: 6836528 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.2238. Min Act: -0.1700
Data Index: 5266424 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.2238. Min Act: -0.1700
Data Index: 6697131 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.2238. Min Act: -0.1700
Data Index: 292037 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.0988. Min Act: -0.1700
Data Index: 689772 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.0988. Min Act: -0.1700
Data Index: 279981 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.0675. Min Act: -0.1700
Data Index: 1425268 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9738. Min Act: -0.1700
Data Index: 1776907 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6300. Min Range: -7.6300
Max Act: 7.0050. Min Act: -0.1700
Data Index: 3762193 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9425. Min Act: -0.1700
Data Index: 6177395 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9738. Min Act: -0.1700
Data Index: 5457573 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9738. Min Act: -0.1700
Data Index: 127524 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9738. Min Act: -0.1700
Data Index: 3724810 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9738. Min Act: -0.1700
Data Index: 3137630 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9425. Min Act: -0.1700
Data Index: 731504 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6300. Min Range: -7.6300
Max Act: 6.9425. Min Act: -0.1700
Data Index: 3459174 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19