Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 356 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.2019. Min Act: -0.1700
Data Index: 3707283 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.2019. Min Act: -0.1700
Data Index: 7566549 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 5708155 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0769. Min Act: -0.1700
Data Index: 2011185 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 581834 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2019. Min Range: -5.2019
Max Act: 5.0457. Min Act: -0.1700
Data Index: 2916976 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9832. Min Act: -0.1700
Data Index: 2421141 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9519. Min Act: -0.1700
Data Index: 3357497 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9519. Min Act: -0.1700
Data Index: 4031498 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 7465588 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1267823 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 4821922 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 3507812 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9207. Min Act: -0.1700
Data Index: 552034 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8894. Min Act: -0.1700
Data Index: 4256402 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.9519. Min Act: -0.1700
Data Index: 4895139 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8894. Min Act: -0.1700
Data Index: 4446995 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8894. Min Act: -0.1700
Data Index: 6647034 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8894. Min Act: -0.1700
Data Index: 3657793 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2019. Min Range: -5.2019
Max Act: 4.8269. Min Act: -0.1700
Data Index: 718573 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19