Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 96 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.3103. Min Act: -0.1700
Data Index: 2807862 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1228. Min Act: -0.1700
Data Index: 6111829 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0915. Min Act: -0.1700
Data Index: 8292587 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9665. Min Act: -0.1700
Data Index: 5375318 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9665. Min Act: -0.1700
Data Index: 2625671 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9353. Min Act: -0.1700
Data Index: 2653952 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9353. Min Act: -0.1700
Data Index: 8465960 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8459136 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2220941 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.9040. Min Act: -0.1700
Data Index: 6127162 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8728. Min Act: -0.1700
Data Index: 629388 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8728. Min Act: -0.1700
Data Index: 8361153 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 1236080 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 6114590 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.7790. Min Act: -0.1700
Data Index: 5366072 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 96871 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 6109925 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.8103. Min Act: -0.1700
Data Index: 7623182 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.7478. Min Act: -0.1700
Data Index: 7296237 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3103. Min Range: -5.3103
Max Act: 4.7790. Min Act: -0.1700
Data Index: 1434558 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19