Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.4759. Min Act: -0.1700
Data Index: 1208784 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.4759. Min Act: -0.1700
Data Index: 5643831 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.4447. Min Act: -0.1700
Data Index: 7369381 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.3197. Min Act: -0.1700
Data Index: 2601432 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.2572. Min Act: -0.1700
Data Index: 8508071 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.2572. Min Act: -0.1700
Data Index: 7352407 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.2259. Min Act: -0.1700
Data Index: 362693 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1634. Min Act: -0.1700
Data Index: 944936 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1947. Min Act: -0.1700
Data Index: 3093735 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1634. Min Act: -0.1700
Data Index: 1869840 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1634. Min Act: -0.1700
Data Index: 5692069 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1322. Min Act: -0.1700
Data Index: 3349271 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1009. Min Act: -0.1700
Data Index: 3372393 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1009. Min Act: -0.1700
Data Index: 6159842 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1009. Min Act: -0.1700
Data Index: 101706 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.1009. Min Act: -0.1700
Data Index: 4314633 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.0697. Min Act: -0.1700
Data Index: 2200706 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.0697. Min Act: -0.1700
Data Index: 7579733 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.0072. Min Act: -0.1700
Data Index: 3491564 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4759. Min Range: -6.4759
Max Act: 6.0384. Min Act: -0.1700
Data Index: 193366 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19