Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2023. Min Range: -7.2023
Max Act: 7.2023. Min Act: -0.1700
Data Index: 7287721 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2023. Min Range: -7.2023
Max Act: 7.0461. Min Act: -0.1700
Data Index: 6769158 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.9523. Min Act: -0.1700
Data Index: 1111654 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.9211. Min Act: -0.1699
Data Index: 7266675 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.8898. Min Act: -0.1700
Data Index: 7476415 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.7648. Min Act: -0.1700
Data Index: 5869502 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.7648. Min Act: -0.1700
Data Index: 2304674 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.6086. Min Act: -0.1700
Data Index: 800774 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.6086. Min Act: -0.1700
Data Index: 4121189 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.6398. Min Act: -0.1700
Data Index: 6274001 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.5773. Min Act: -0.1700
Data Index: 2853292 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.5461. Min Act: -0.1700
Data Index: 3270457 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.5461. Min Act: -0.1700
Data Index: 3280866 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4836. Min Act: -0.1700
Data Index: 3035498 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4523. Min Act: -0.1700
Data Index: 3270452 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4836. Min Act: -0.1700
Data Index: 4374029 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.5148. Min Act: -0.1700
Data Index: 3366081 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4836. Min Act: -0.1700
Data Index: 1310901 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4523. Min Act: -0.1700
Data Index: 4043280 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2023. Min Range: -7.2023
Max Act: 6.4523. Min Act: -0.1700
Data Index: 4043267 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19