Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 134 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.4837. Min Act: -0.1700
Data Index: 2555854 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.3426. Min Act: -0.1700
Data Index: 2528643 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.3269. Min Act: -0.1700
Data Index: 8292864 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2955. Min Act: -0.1700
Data Index: 3231372 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2798. Min Act: -0.1700
Data Index: 5366646 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2798. Min Act: -0.1700
Data Index: 3347186 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2641. Min Act: -0.1700
Data Index: 5565243 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2798. Min Act: -0.1700
Data Index: 6835940 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2484. Min Act: -0.1700
Data Index: 5607233 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2484. Min Act: -0.1700
Data Index: 7740341 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2327. Min Act: -0.1700
Data Index: 823225 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2484. Min Act: -0.1700
Data Index: 3519281 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2327. Min Act: -0.1700
Data Index: 200963 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2170. Min Act: -0.1700
Data Index: 986938 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2013. Min Act: -0.1700
Data Index: 5156744 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2013. Min Act: -0.1700
Data Index: 686371 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.2013. Min Act: -0.1700
Data Index: 3585313 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.1855. Min Act: -0.1700
Data Index: 1759356 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.1855. Min Act: -0.1700
Data Index: 2110379 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4837. Min Range: -3.4837
Max Act: 3.1541. Min Act: -0.1700
Data Index: 225648 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19