Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2075 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.6539. Min Act: -0.1700
Data Index: 4700461 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.5600. Min Act: -0.1700
Data Index: 4290879 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.5600. Min Act: -0.1700
Data Index: 8781103 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.5600. Min Act: -0.1700
Data Index: 5377359 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.5600. Min Act: -0.1700
Data Index: 6452024 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4973. Min Act: -0.1700
Data Index: 5513975 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4973. Min Act: -0.1700
Data Index: 1498142 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.5287. Min Act: -0.1700
Data Index: 99891 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4660. Min Act: -0.1700
Data Index: 3426722 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4660. Min Act: -0.1700
Data Index: 4161703 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4660. Min Act: -0.1700
Data Index: 1870044 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4660. Min Act: -0.1700
Data Index: 4615951 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4347. Min Act: -0.1700
Data Index: 1809053 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4347. Min Act: -0.1700
Data Index: 1345686 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4033. Min Act: -0.1700
Data Index: 5832812 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4033. Min Act: -0.1700
Data Index: 6150971 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4033. Min Act: -0.1700
Data Index: 5522575 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4033. Min Act: -0.1700
Data Index: 4659933 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.3720. Min Act: -0.1700
Data Index: 2866706 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6539. Min Range: -3.6539
Max Act: 3.4347. Min Act: -0.1700
Data Index: 4913299 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19