Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.6277. Min Act: -0.1700
Data Index: 877405 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.4402. Min Act: -0.1700
Data Index: 1467071 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.4714. Min Act: -0.1700
Data Index: 5696020 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.4402. Min Act: -0.1700
Data Index: 8630125 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.4089. Min Act: -0.1700
Data Index: 6043621 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.3464. Min Act: -0.1700
Data Index: 5958410 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2527. Min Act: -0.1700
Data Index: 5783677 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6139621 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2527. Min Act: -0.1700
Data Index: 6197666 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1650618 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2214. Min Act: -0.1700
Data Index: 460735 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1902. Min Act: -0.1700
Data Index: 1101798 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1902. Min Act: -0.1700
Data Index: 28054 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1902. Min Act: -0.1700
Data Index: 1347593 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1345990 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1902. Min Act: -0.1700
Data Index: 4004644 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1589. Min Act: -0.1700
Data Index: 593169 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.1589. Min Act: -0.1700
Data Index: 1169073 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3327936 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6277. Min Range: -6.6277
Max Act: 6.0964. Min Act: -0.1700
Data Index: 5910218 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19