Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5994. Min Range: -8.5994
Max Act: 8.5994. Min Act: -0.1700
Data Index: 4635272 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5994. Min Range: -8.5994
Max Act: 7.1619. Min Act: -0.1700
Data Index: 2692590 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5994. Min Range: -8.5994
Max Act: 7.0369. Min Act: -0.1700
Data Index: 5221435 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5994. Min Range: -8.5994
Max Act: 7.0057. Min Act: -0.1700
Data Index: 4578258 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5994. Min Range: -8.5994
Max Act: 7.0057. Min Act: -0.1700
Data Index: 1519099 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.9119. Min Act: -0.1700
Data Index: 1546596 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.7244. Min Act: -0.1700
Data Index: 6300645 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.7244. Min Act: -0.1700
Data Index: 2276180 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.7557. Min Act: -0.1700
Data Index: 4081819 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.6932. Min Act: -0.1700
Data Index: 7061305 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.6307. Min Act: -0.1700
Data Index: 3218871 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4965923 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5994. Min Act: -0.1700
Data Index: 8045786 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5682. Min Act: -0.1700
Data Index: 6066471 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.6307. Min Act: -0.1700
Data Index: 7926336 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5994. Min Act: -0.1700
Data Index: 4880177 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.6307. Min Act: -0.1700
Data Index: 3037496 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5682. Min Act: -0.1700
Data Index: 4213043 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5994. Min Act: -0.1700
Data Index: 6799954 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5994. Min Range: -8.5994
Max Act: 6.5994. Min Act: -0.1700
Data Index: 5845693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19