Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0868. Min Range: -8.0868
Max Act: 8.0868. Min Act: -0.1700
Data Index: 1676838 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.8993. Min Act: -0.1700
Data Index: 5263076 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.8993. Min Act: -0.1700
Data Index: 4910490 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.6493. Min Act: -0.1700
Data Index: 8452734 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.6493. Min Act: -0.1700
Data Index: 5332216 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.6493. Min Act: -0.1700
Data Index: 6670237 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5868. Min Act: -0.1700
Data Index: 6413158 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.6493. Min Act: -0.1700
Data Index: 4733046 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5868. Min Act: -0.1700
Data Index: 3804333 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5868. Min Act: -0.1700
Data Index: 686598 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5868. Min Act: -0.1700
Data Index: 4206514 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5243. Min Act: -0.1700
Data Index: 3681776 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5243. Min Act: -0.1700
Data Index: 5667464 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.5243. Min Act: -0.1700
Data Index: 1165970 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4618. Min Act: -0.1700
Data Index: 3231545 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4618. Min Act: -0.1700
Data Index: 3422502 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4618. Min Act: -0.1700
Data Index: 2984092 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4618. Min Act: -0.1700
Data Index: 5561230 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4306. Min Act: -0.1700
Data Index: 1480969 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0868. Min Range: -8.0868
Max Act: 7.4306. Min Act: -0.1700
Data Index: 5196730 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19