Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.3582. Min Act: -0.1695
Data Index: 2737512 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2640. Min Act: -0.1700
Data Index: 648281 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2326. Min Act: -0.1700
Data Index: 6896700 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2640. Min Act: -0.1700
Data Index: 5090366 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2011. Min Act: -0.1700
Data Index: 646444 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2011. Min Act: -0.1700
Data Index: 549254 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1697. Min Act: -0.1700
Data Index: 469875 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.2326. Min Act: -0.1699
Data Index: 7578692 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1700
Data Index: 2389048 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1697. Min Act: -0.1699
Data Index: 3500477 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1697. Min Act: -0.1693
Data Index: 1636427 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1684
Data Index: 2416953 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1697. Min Act: -0.1689
Data Index: 1365010 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1700
Data Index: 1617403 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1700
Data Index: 7690929 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1684
Data Index: 4119452 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1677
Data Index: 950904 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1382. Min Act: -0.1700
Data Index: 2114100 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.1067. Min Act: -0.1700
Data Index: 3220393 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3582. Min Range: -3.3582
Max Act: 3.0752. Min Act: -0.1686
Data Index: 5888024 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19