Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.8507. Min Act: -0.1700
Data Index: 8192368 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.7569. Min Act: -0.1700
Data Index: 4000286 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.7257. Min Act: -0.1700
Data Index: 17479 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.7257. Min Act: -0.1700
Data Index: 7067658 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.6007. Min Act: -0.1700
Data Index: 7803902 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.5069. Min Act: -0.1700
Data Index: 2677557 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4757. Min Act: -0.1700
Data Index: 6246684 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4757. Min Act: -0.1700
Data Index: 4521099 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4757. Min Act: -0.1700
Data Index: 6415698 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4444. Min Act: -0.1700
Data Index: 2094396 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4444. Min Act: -0.1700
Data Index: 4550812 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4444. Min Act: -0.1700
Data Index: 6401820 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4444. Min Act: -0.1700
Data Index: 3442861 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4444. Min Act: -0.1700
Data Index: 2598011 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.4132. Min Act: -0.1700
Data Index: 6020133 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.3819. Min Act: -0.1700
Data Index: 3472598 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.3819. Min Act: -0.1700
Data Index: 6848173 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.3819. Min Act: -0.1700
Data Index: 108347 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.3507. Min Act: -0.1700
Data Index: 4890848 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8507. Min Range: -6.8507
Max Act: 6.3507. Min Act: -0.1700
Data Index: 7843216 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19