Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1093 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.3722. Min Act: -0.1700
Data Index: 1311926 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.3722. Min Act: -0.1700
Data Index: 4307089 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.0909. Min Act: -0.1700
Data Index: 1090345 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.0284. Min Act: -0.1700
Data Index: 6468242 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3722. Min Range: -4.3722
Max Act: 4.0284. Min Act: -0.1700
Data Index: 2342026 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9972. Min Act: -0.1700
Data Index: 6369521 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9659. Min Act: -0.1700
Data Index: 8716968 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9346. Min Act: -0.1700
Data Index: 7819415 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9346. Min Act: -0.1700
Data Index: 528331 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9346. Min Act: -0.1700
Data Index: 7622153 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.9034. Min Act: -0.1700
Data Index: 8430415 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8721. Min Act: -0.1700
Data Index: 8430411 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7470. Min Act: -0.1700
Data Index: 636787 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7470. Min Act: -0.1700
Data Index: 3790539 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8096. Min Act: -0.1700
Data Index: 8367588 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8096. Min Act: -0.1700
Data Index: 4932523 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7783. Min Act: -0.1700
Data Index: 8638407 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7314. Min Act: -0.1700
Data Index: 2069724 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.8096. Min Act: -0.1700
Data Index: 935617 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3722. Min Range: -4.3722
Max Act: 3.7314. Min Act: -0.1700
Data Index: 2516669 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19