Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6394 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.5759. Min Act: -0.1700
Data Index: 7539838 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.3884. Min Act: -0.1700
Data Index: 3383190 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.1384. Min Act: -0.1700
Data Index: 7903438 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.1384. Min Act: -0.1700
Data Index: 6012412 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.0759. Min Act: -0.1700
Data Index: 3881224 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5759. Min Range: -9.5759
Max Act: 9.0759. Min Act: -0.1700
Data Index: 4473739 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8259. Min Act: -0.1700
Data Index: 8016900 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8884. Min Act: -0.1700
Data Index: 4647988 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8884. Min Act: -0.1700
Data Index: 8092611 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8884. Min Act: -0.1700
Data Index: 3003637 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8259. Min Act: -0.1700
Data Index: 7431567 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 2110870 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.8259. Min Act: -0.1700
Data Index: 3117700 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 233627 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 952847 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7009. Min Act: -0.1700
Data Index: 2693540 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7009. Min Act: -0.1700
Data Index: 2591595 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.7009. Min Act: -0.1700
Data Index: 1333099 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 4678146 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5759. Min Range: -9.5759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 7535386 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19