Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.3610. Min Act: -0.1700
Data Index: 814636 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.3298. Min Act: -0.1700
Data Index: 7210721 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.1110. Min Act: -0.1700
Data Index: 3844009 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3610. Min Range: -6.3610
Max Act: 6.0485. Min Act: -0.1700
Data Index: 6256568 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9548. Min Act: -0.1700
Data Index: 7080278 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.9235. Min Act: -0.1700
Data Index: 5062887 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.7985. Min Act: -0.1700
Data Index: 8668835 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.7985. Min Act: -0.1700
Data Index: 7838813 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.7673. Min Act: -0.1700
Data Index: 4258817 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.6110. Min Act: -0.1700
Data Index: 3867201 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.6110. Min Act: -0.1700
Data Index: 6166860 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.5798. Min Act: -0.1700
Data Index: 6226461 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.5798. Min Act: -0.1700
Data Index: 1946805 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.4860. Min Act: -0.1700
Data Index: 6312272 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.5173. Min Act: -0.1700
Data Index: 3252383 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.5173. Min Act: -0.1700
Data Index: 1389583 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.4860. Min Act: -0.1700
Data Index: 2821814 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.4548. Min Act: -0.1700
Data Index: 789351 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.4235. Min Act: -0.1700
Data Index: 3379635 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3610. Min Range: -6.3610
Max Act: 5.3923. Min Act: -0.1700
Data Index: 7677370 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19