Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.9046. Min Act: -0.1700
Data Index: 1515698 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.9046. Min Act: -0.1700
Data Index: 3493261 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.9046. Min Act: -0.1700
Data Index: 7864347 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.8421. Min Act: -0.1700
Data Index: 3904163 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.8421. Min Act: -0.1700
Data Index: 8828109 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.9046. Min Act: -0.1698
Data Index: 5190827 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.8421. Min Act: -0.1700
Data Index: 4903246 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.8421. Min Act: -0.1700
Data Index: 7038598 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7796. Min Act: -0.1700
Data Index: 5176982 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7796. Min Act: -0.1697
Data Index: 6325233 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 2159063 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1699
Data Index: 261291 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 8045070 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1699
Data Index: 3905999 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 2010588 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 7387095 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 7521015 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 7426199 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.6546. Min Act: -0.1700
Data Index: 7360876 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9046. Min Range: -7.9046
Max Act: 7.7171. Min Act: -0.1700
Data Index: 3044400 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19