Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.1201. Min Range: -12.1201
Max Act: 12.1201. Min Act: -0.1700
Data Index: 1735214 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1201. Min Range: -12.1201
Max Act: 11.3076. Min Act: -0.1700
Data Index: 1735211 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1201. Min Range: -12.1201
Max Act: 11.2451. Min Act: -0.1700
Data Index: 5702795 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1201. Min Range: -12.1201
Max Act: 11.2451. Min Act: -0.1700
Data Index: 8293242 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.9951. Min Act: -0.1700
Data Index: 5503961 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.9951. Min Act: -0.1700
Data Index: 888544 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.5576. Min Act: -0.1700
Data Index: 4644233 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.5576. Min Act: -0.1700
Data Index: 5049456 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.3701. Min Act: -0.1700
Data Index: 8257911 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.3076. Min Act: -0.1700
Data Index: 2236968 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.3076. Min Act: -0.1700
Data Index: 7403876 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.2451. Min Act: -0.1700
Data Index: 3658417 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.1826. Min Act: -0.1700
Data Index: 8672494 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.1201. Min Act: -0.1700
Data Index: 1939512 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1201. Min Range: -12.1201
Max Act: 10.1201. Min Act: -0.1700
Data Index: 8755994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1201. Min Range: -12.1201
Max Act: 9.9326. Min Act: -0.1700
Data Index: 5311671 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1201. Min Range: -12.1201
Max Act: 9.9951. Min Act: -0.1700
Data Index: 3892757 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1201. Min Range: -12.1201
Max Act: 9.9951. Min Act: -0.1700
Data Index: 628169 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1201. Min Range: -12.1201
Max Act: 9.9951. Min Act: -0.1700
Data Index: 8050596 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1201. Min Range: -12.1201
Max Act: 9.9326. Min Act: -0.1700
Data Index: 8158191 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19