Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.8773. Min Act: -0.1700
Data Index: 5690957 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.7523. Min Act: -0.1700
Data Index: 5247042 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.7523. Min Act: -0.1700
Data Index: 5651604 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.5023. Min Act: -0.1700
Data Index: 4389030 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3773. Min Act: -0.1700
Data Index: 29535 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3773. Min Act: -0.1700
Data Index: 8073558 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3148. Min Act: -0.1700
Data Index: 2428824 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3148. Min Act: -0.1700
Data Index: 1391930 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3148. Min Act: -0.1700
Data Index: 505870 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.3148. Min Act: -0.1700
Data Index: 5281152 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.2523. Min Act: -0.1700
Data Index: 4886642 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.2523. Min Act: -0.1700
Data Index: 6724843 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.2523. Min Act: -0.1700
Data Index: 6959327 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 5567695 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1273. Min Act: -0.1700
Data Index: 6324181 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 687016 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 1635746 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 8268931 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 8482777 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8773. Min Range: -8.8773
Max Act: 8.1898. Min Act: -0.1700
Data Index: 1107718 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19