Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1345. Min Range: -5.1345
Max Act: 5.1345. Min Act: -0.1700
Data Index: 2579044 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1345. Min Range: -5.1345
Max Act: 5.1345. Min Act: -0.1700
Data Index: 4101147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1345. Min Range: -5.1345
Max Act: 5.0720. Min Act: -0.1700
Data Index: 6632192 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1345. Min Range: -5.1345
Max Act: 5.0720. Min Act: -0.1700
Data Index: 7397252 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1345. Min Range: -5.1345
Max Act: 5.0408. Min Act: -0.1700
Data Index: 8520064 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3619324 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.9783. Min Act: -0.1700
Data Index: 5052695 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.9783. Min Act: -0.1700
Data Index: 4979364 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.9158. Min Act: -0.1700
Data Index: 4135592 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.9158. Min Act: -0.1700
Data Index: 3503016 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8845. Min Act: -0.1700
Data Index: 4858678 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 6859376 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 5222713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 5649310 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 7160293 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 1156190 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 1053350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8533. Min Act: -0.1700
Data Index: 6214810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.7908. Min Act: -0.1700
Data Index: 3104330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1345. Min Range: -5.1345
Max Act: 4.8220. Min Act: -0.1700
Data Index: 3510773 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19