Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.5584. Min Act: -0.1700
Data Index: 3609395 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.5271. Min Act: -0.1700
Data Index: 3854312 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.4646. Min Act: -0.1700
Data Index: 3497501 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.4646. Min Act: -0.1700
Data Index: 8452929 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.4334. Min Act: -0.1700
Data Index: 7129987 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.4334. Min Act: -0.1700
Data Index: 620352 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.4021. Min Act: -0.1700
Data Index: 705407 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3709. Min Act: -0.1700
Data Index: 5866053 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3709. Min Act: -0.1700
Data Index: 3575571 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3709. Min Act: -0.1700
Data Index: 3480381 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 7763863 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3709. Min Act: -0.1700
Data Index: 5904438 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3709. Min Act: -0.1700
Data Index: 6560475 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 1674445 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 5691767 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3084. Min Act: -0.1700
Data Index: 8694468 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 6083124 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 2268575 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3396. Min Act: -0.1700
Data Index: 3528614 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5584. Min Range: -4.5584
Max Act: 4.3084. Min Act: -0.1700
Data Index: 2501707 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19