Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.8636. Min Act: -0.1700
Data Index: 6459828 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 370922 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 4229936 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.3323. Min Act: -0.1700
Data Index: 5892425 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.3323. Min Act: -0.1700
Data Index: 2295268 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2698. Min Act: -0.1700
Data Index: 1196856 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2698. Min Act: -0.1700
Data Index: 4987054 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 7288700 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 5043104 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 4785121 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2386. Min Act: -0.1700
Data Index: 5665812 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 2337822 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 6806094 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2386. Min Act: -0.1700
Data Index: 1007311 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 3772857 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 1489507 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.2073. Min Act: -0.1700
Data Index: 7418820 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.1761. Min Act: -0.1700
Data Index: 3983040 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.1761. Min Act: -0.1700
Data Index: 6634697 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8636. Min Range: -6.8636
Max Act: 6.1761. Min Act: -0.1700
Data Index: 7018100 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19