Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7358142 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.8447. Min Act: -0.1700
Data Index: 1820955 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.8135. Min Act: -0.1700
Data Index: 2585476 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7822. Min Act: -0.1700
Data Index: 4367234 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4097670 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7510. Min Act: -0.1700
Data Index: 6594371 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7510. Min Act: -0.1700
Data Index: 1407542 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7197. Min Act: -0.1700
Data Index: 3308886 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7197. Min Act: -0.1700
Data Index: 2045683 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.7510. Min Act: -0.1700
Data Index: 6873102 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6885. Min Act: -0.1700
Data Index: 3339999 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5355412 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6885. Min Act: -0.1700
Data Index: 2984111 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6572. Min Act: -0.1700
Data Index: 5903979 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5072087 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3214230 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.5947. Min Act: -0.1700
Data Index: 8034336 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.6260. Min Act: -0.1700
Data Index: 2305146 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.5947. Min Act: -0.1700
Data Index: 4304186 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9697. Min Range: -5.9697
Max Act: 5.5947. Min Act: -0.1700
Data Index: 3323524 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19