Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.4581. Min Act: -0.1700
Data Index: 3032829 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.4268. Min Act: -0.1700
Data Index: 8644098 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3643. Min Act: -0.1700
Data Index: 5633473 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3956. Min Act: -0.1700
Data Index: 5721535 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1900838 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3956. Min Act: -0.1700
Data Index: 2847874 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3643. Min Act: -0.1700
Data Index: 4814550 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3331. Min Act: -0.1700
Data Index: 5654396 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3018. Min Act: -0.1700
Data Index: 4833963 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3331. Min Act: -0.1700
Data Index: 5633474 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.3331. Min Act: -0.1700
Data Index: 6382848 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2393. Min Act: -0.1700
Data Index: 31442 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 1156251 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 5958772 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 138005 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 2525700 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 667556 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2393. Min Act: -0.1700
Data Index: 1975450 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2706. Min Act: -0.1700
Data Index: 6372248 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4581. Min Range: -4.4581
Max Act: 4.2393. Min Act: -0.1700
Data Index: 6246511 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19