Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.6590. Min Act: -0.1700
Data Index: 7122198 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.6433. Min Act: -0.1700
Data Index: 4570370 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5338. Min Act: -0.1700
Data Index: 2453508 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.5181. Min Act: -0.1700
Data Index: 7393587 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4868. Min Act: -0.1700
Data Index: 928667 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4711. Min Act: -0.1700
Data Index: 1411603 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4554. Min Act: -0.1700
Data Index: 914903 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4398. Min Act: -0.1700
Data Index: 6233271 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4241. Min Act: -0.1700
Data Index: 3130682 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.4241. Min Act: -0.1700
Data Index: 6841462 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3927. Min Act: -0.1700
Data Index: 2827526 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3614. Min Act: -0.1700
Data Index: 5744133 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3457. Min Act: -0.1700
Data Index: 2900942 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3300. Min Act: -0.1700
Data Index: 8649365 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3457. Min Act: -0.1700
Data Index: 4896913 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.3143. Min Act: -0.1700
Data Index: 1405485 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.2672. Min Act: -0.1700
Data Index: 1435018 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.2672. Min Act: -0.1700
Data Index: 2354085 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.2515. Min Act: -0.1700
Data Index: 8816637 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6590. Min Range: -3.6590
Max Act: 3.2515. Min Act: -0.1700
Data Index: 7202369 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19