Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.5685. Min Act: -0.1700
Data Index: 6799094 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.2560. Min Act: -0.1700
Data Index: 1141324 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.1935. Min Act: -0.1700
Data Index: 6679474 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.2560. Min Act: -0.1700
Data Index: 179438 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.0060. Min Act: -0.1700
Data Index: 7059659 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.0060. Min Act: -0.1700
Data Index: 6255790 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5685. Min Range: -9.5685
Max Act: 9.0060. Min Act: -0.1700
Data Index: 7842701 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.9435. Min Act: -0.1700
Data Index: 1995559 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8810. Min Act: -0.1700
Data Index: 1961463 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8810. Min Act: -0.1700
Data Index: 8111342 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8185. Min Act: -0.1700
Data Index: 6045517 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8185. Min Act: -0.1700
Data Index: 4461889 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.7560. Min Act: -0.1700
Data Index: 7967813 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8810. Min Act: -0.1700
Data Index: 7315994 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8185. Min Act: -0.1700
Data Index: 4865725 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.8185. Min Act: -0.1700
Data Index: 2071956 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.7560. Min Act: -0.1700
Data Index: 3522519 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.6935. Min Act: -0.1700
Data Index: 548748 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.7560. Min Act: -0.1700
Data Index: 7281421 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5685. Min Range: -9.5685
Max Act: 8.7560. Min Act: -0.1700
Data Index: 7030564 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19