Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.5298. Min Act: -0.1700
Data Index: 4263419 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.4360. Min Act: -0.1700
Data Index: 1146536 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.4360. Min Act: -0.1700
Data Index: 5868546 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.4048. Min Act: -0.1700
Data Index: 5368203 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.3423. Min Act: -0.1700
Data Index: 8332746 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.3110. Min Act: -0.1700
Data Index: 5099914 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.2798. Min Act: -0.1699
Data Index: 3896072 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.3110. Min Act: -0.1700
Data Index: 4092930 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.2485. Min Act: -0.1700
Data Index: 1094703 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.2485. Min Act: -0.1700
Data Index: 7198518 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.2485. Min Act: -0.1700
Data Index: 930585 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.2485. Min Act: -0.1700
Data Index: 63923 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 2256333 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 7784525 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 2906858 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1548. Min Act: -0.1700
Data Index: 4836461 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 3065899 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 3128127 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 8470708 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5298. Min Range: -4.5298
Max Act: 4.1860. Min Act: -0.1700
Data Index: 2058408 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19