Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0868. Min Range: -5.0868
Max Act: 5.0868. Min Act: -0.1700
Data Index: 20424 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0868. Min Range: -5.0868
Max Act: 5.0556. Min Act: -0.1700
Data Index: 1758918 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8368. Min Act: -0.1700
Data Index: 5888400 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8056. Min Act: -0.1700
Data Index: 4088824 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 3972605 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 5106921 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2973320 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1687484 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1428060 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6806. Min Act: -0.1700
Data Index: 8288023 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6493. Min Act: -0.1700
Data Index: 6789595 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1699
Data Index: 5315891 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6493. Min Act: -0.1700
Data Index: 710566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6493. Min Act: -0.1700
Data Index: 2518847 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6181. Min Act: -0.1700
Data Index: 6353764 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6493. Min Act: -0.1700
Data Index: 3563114 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6493. Min Act: -0.1700
Data Index: 6217334 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6181. Min Act: -0.1700
Data Index: 1340235 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6181. Min Act: -0.1700
Data Index: 4446039 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6181. Min Act: -0.1700
Data Index: 6763171 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19