Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5716. Min Act: -0.1700
Data Index: 6850922 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5716. Min Act: -0.1700
Data Index: 6836353 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5247. Min Act: -0.1700
Data Index: 7585622 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3679. Min Act: -0.1700
Data Index: 3982050 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3679. Min Act: -0.1700
Data Index: 442530 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3679. Min Act: -0.1700
Data Index: 500632 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3523. Min Act: -0.1700
Data Index: 5626033 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3366. Min Act: -0.1700
Data Index: 5686628 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3209. Min Act: -0.1700
Data Index: 6704834 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3209. Min Act: -0.1700
Data Index: 6970331 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3209. Min Act: -0.1700
Data Index: 6344095 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2738. Min Act: -0.1700
Data Index: 1312946 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3052. Min Act: -0.1700
Data Index: 3628948 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2581. Min Act: -0.1700
Data Index: 4417898 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2738. Min Act: -0.1700
Data Index: 4561875 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2581. Min Act: -0.1700
Data Index: 5796339 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2424. Min Act: -0.1700
Data Index: 1892751 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2581. Min Act: -0.1700
Data Index: 6839335 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2424. Min Act: -0.1700
Data Index: 6293538 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.2581. Min Act: -0.1700
Data Index: 2113565 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19