Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.2820. Min Act: -0.1700
Data Index: 4620703 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.2195. Min Act: -0.1700
Data Index: 728538 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7195392 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 2293792 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 5150377 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 3756654 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 7105963 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 2943145 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 1359081 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5920810 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5065319 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 3588451 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0633. Min Act: -0.1700
Data Index: 6990214 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 1203020 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 888948 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0633. Min Act: -0.1700
Data Index: 7901046 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 3519041 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 1463032 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0320. Min Act: -0.1700
Data Index: 4300210 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0633. Min Act: -0.1700
Data Index: 2104292 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19