Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.9513. Min Act: -0.1700
Data Index: 6267097 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.9200. Min Act: -0.1700
Data Index: 3235760 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.8888. Min Act: -0.1700
Data Index: 3803510 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7949. Min Act: -0.1700
Data Index: 2759270 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.8262. Min Act: -0.1700
Data Index: 6192394 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7949. Min Act: -0.1700
Data Index: 8668822 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7949. Min Act: -0.1700
Data Index: 7830363 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7324. Min Act: -0.1700
Data Index: 4310474 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7637. Min Act: -0.1700
Data Index: 6141383 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 6992324 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 182611 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7324. Min Act: -0.1700
Data Index: 6763350 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7324. Min Act: -0.1700
Data Index: 6728986 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7324. Min Act: -0.1700
Data Index: 1089281 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7177548 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 4728382 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 8648921 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7167. Min Act: -0.1700
Data Index: 1691175 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.7324. Min Act: -0.1700
Data Index: 609888 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9513. Min Range: -3.9513
Max Act: 3.6855. Min Act: -0.1700
Data Index: 3929777 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19