Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0535. Min Range: -5.0535
Max Act: 5.0535. Min Act: -0.1700
Data Index: 6883324 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9910. Min Act: -0.1700
Data Index: 1677778 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9597. Min Act: -0.1700
Data Index: 858584 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9910. Min Act: -0.1700
Data Index: 6458337 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0535. Min Range: -5.0535
Max Act: 5.0222. Min Act: -0.1700
Data Index: 1106824 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9910. Min Act: -0.1700
Data Index: 8744400 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9597. Min Act: -0.1700
Data Index: 8299061 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2666360 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 6117586 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9910. Min Act: -0.1700
Data Index: 3398974 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1961180 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 8301756 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 4322372 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2016990 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2684961 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8972. Min Act: -0.1700
Data Index: 1894543 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1656783 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 3872846 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8972. Min Act: -0.1700
Data Index: 1643124 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8972. Min Act: -0.1700
Data Index: 61079 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19