Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.9017. Min Act: -0.1700
Data Index: 6016935 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8847. Min Act: -0.1700
Data Index: 4968079 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8505. Min Act: -0.1700
Data Index: 8751933 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8419. Min Act: -0.1700
Data Index: 5598977 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8247. Min Act: -0.1696
Data Index: 4236389 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8162. Min Act: -0.1700
Data Index: 814552 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8162. Min Act: -0.1700
Data Index: 8547580 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8162. Min Act: -0.1700
Data Index: 4212041 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.8076. Min Act: -0.1700
Data Index: 2970446 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7904. Min Act: -0.1700
Data Index: 3964329 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7818. Min Act: -0.1700
Data Index: 6651984 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7731. Min Act: -0.1700
Data Index: 1978696 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7731. Min Act: -0.1700
Data Index: 6171487 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7731. Min Act: -0.1700
Data Index: 3179029 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7731. Min Act: -0.1700
Data Index: 918771 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7731. Min Act: -0.1700
Data Index: 7459252 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7645. Min Act: -0.1691
Data Index: 6655552 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7645. Min Act: -0.1700
Data Index: 6433125 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7818. Min Act: -0.1700
Data Index: 2223657 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9017. Min Range: -1.9017
Max Act: 1.7645. Min Act: -0.1700
Data Index: 6435036 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19