Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4219. Min Range: -7.4219
Max Act: 7.4219. Min Act: -0.1700
Data Index: 5134786 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.8594. Min Act: -0.1700
Data Index: 8795240 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.8281. Min Act: -0.1700
Data Index: 6779066 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.7344. Min Act: -0.1700
Data Index: 1880537 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.7344. Min Act: -0.1700
Data Index: 2827123 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.7344. Min Act: -0.1700
Data Index: 7937872 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.6406. Min Act: -0.1700
Data Index: 5426359 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.6094. Min Act: -0.1700
Data Index: 6893777 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.6094. Min Act: -0.1700
Data Index: 8565616 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.6094. Min Act: -0.1700
Data Index: 1508006 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.6094. Min Act: -0.1700
Data Index: 3835666 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2812038 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5469. Min Act: -0.1700
Data Index: 4854371 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4886442 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5469. Min Act: -0.1700
Data Index: 6063114 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5469. Min Act: -0.1700
Data Index: 6062254 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5469. Min Act: -0.1700
Data Index: 7266549 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5156. Min Act: -0.1700
Data Index: 1405192 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5156. Min Act: -0.1700
Data Index: 6101086 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4219. Min Range: -7.4219
Max Act: 6.5156. Min Act: -0.1700
Data Index: 7369719 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19