Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2464. Min Range: -5.2464
Max Act: 5.2464. Min Act: -0.1700
Data Index: 6645456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.8089. Min Act: -0.1700
Data Index: 7113371 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.6527. Min Act: -0.1700
Data Index: 6645449 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.6214. Min Act: -0.1700
Data Index: 5008183 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.5902. Min Act: -0.1700
Data Index: 7668060 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.6214. Min Act: -0.1700
Data Index: 4365828 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.5589. Min Act: -0.1700
Data Index: 965995 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 717347 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 2508286 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 5748548 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 1380442 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4964. Min Act: -0.1700
Data Index: 3176860 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4339. Min Act: -0.1700
Data Index: 3615783 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4339. Min Act: -0.1700
Data Index: 2947536 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4652. Min Act: -0.1700
Data Index: 445010 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4652. Min Act: -0.1700
Data Index: 4395240 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4652. Min Act: -0.1700
Data Index: 6077475 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4339. Min Act: -0.1700
Data Index: 3242611 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4339. Min Act: -0.1700
Data Index: 2001540 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2464. Min Range: -5.2464
Max Act: 4.4339. Min Act: -0.1700
Data Index: 4649826 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19