Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.3985. Min Act: -0.1700
Data Index: 7377015 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.3985. Min Act: -0.1699
Data Index: 7377016 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.3659. Min Act: -0.1697
Data Index: 4008527 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.3659. Min Act: -0.1700
Data Index: 2727932 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2673. Min Act: -0.1699
Data Index: 7782523 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2508. Min Act: -0.1700
Data Index: 172969 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2508. Min Act: -0.1696
Data Index: 5883248 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2673. Min Act: -0.1700
Data Index: 7676406 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2673. Min Act: -0.1700
Data Index: 4817965 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2508. Min Act: -0.1700
Data Index: 2374119 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2673. Min Act: -0.1700
Data Index: 4427973 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2508. Min Act: -0.1700
Data Index: 4054000 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2342. Min Act: -0.1700
Data Index: 2258048 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2177. Min Act: -0.1687
Data Index: 604803 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2177. Min Act: -0.1700
Data Index: 3166362 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2177. Min Act: -0.1700
Data Index: 1629791 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2011. Min Act: -0.1700
Data Index: 8067701 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2177. Min Act: -0.1692
Data Index: 3737224 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2342. Min Act: -0.1699
Data Index: 767185 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3985. Min Range: -2.3985
Max Act: 2.2177. Min Act: -0.1700
Data Index: 6318478 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19