Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9243. Min Act: -0.1700
Data Index: 4014425 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9555. Min Act: -0.1700
Data Index: 7667201 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 5599603 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4113261 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7941021 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 8562098 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 2650150 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4786430 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7368. Min Act: -0.1700
Data Index: 1847432 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7055. Min Act: -0.1700
Data Index: 5876668 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6743. Min Act: -0.1700
Data Index: 1602316 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 6623697 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 158996 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6118. Min Act: -0.1700
Data Index: 3777126 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 5610181 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6743. Min Act: -0.1700
Data Index: 3269886 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 3505240 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 7410128 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6430. Min Act: -0.1700
Data Index: 3997513 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.6743. Min Act: -0.1700
Data Index: 245599 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19