Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.5148. Min Act: -0.1700
Data Index: 3146647 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4523. Min Act: -0.1700
Data Index: 5822855 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4835. Min Act: -0.1700
Data Index: 729523 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4835. Min Act: -0.1700
Data Index: 4321344 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4835. Min Act: -0.1700
Data Index: 8589195 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4523. Min Act: -0.1700
Data Index: 3322993 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3898. Min Act: -0.1700
Data Index: 4510630 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.4210. Min Act: -0.1700
Data Index: 3472941 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3898. Min Act: -0.1700
Data Index: 5542034 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3898. Min Act: -0.1700
Data Index: 1143897 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 5386597 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 5992472 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 8231132 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 4773070 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 516476 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 76435 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3585. Min Act: -0.1700
Data Index: 3855352 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.2648. Min Act: -0.1700
Data Index: 3662203 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3273. Min Act: -0.1700
Data Index: 4504417 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5148. Min Range: -4.5148
Max Act: 4.3273. Min Act: -0.1700
Data Index: 1831433 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19