Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.8548. Min Act: -0.1620
Data Index: 3617270 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.7611. Min Act: -0.1235
Data Index: 6512380 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.7298. Min Act: -0.1690
Data Index: 3409671 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.6986. Min Act: -0.1699
Data Index: 4847722 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.6673. Min Act: -0.1433
Data Index: 476347 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.6048. Min Act: -0.1689
Data Index: 7542880 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.6048. Min Act: -0.1700
Data Index: 3629862 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.6048. Min Act: -0.1697
Data Index: 5202158 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.5736. Min Act: -0.1700
Data Index: 4952078 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.5111. Min Act: -0.1690
Data Index: 826251 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4798. Min Act: -0.1668
Data Index: 5019150 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4486. Min Act: -0.1700
Data Index: 3766488 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4173. Min Act: -0.1654
Data Index: 2925817 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4486. Min Act: -0.1658
Data Index: 5202160 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4486. Min Act: -0.1421
Data Index: 4916342 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.4173. Min Act: -0.1618
Data Index: 476340 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.3861. Min Act: -0.1700
Data Index: 8343354 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.3861. Min Act: -0.1700
Data Index: 4430450 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.3861. Min Act: -0.1696
Data Index: 1386407 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8548. Min Range: -6.8548
Max Act: 6.3548. Min Act: -0.1696
Data Index: 5202161 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19