Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.7176. Min Act: -0.1700
Data Index: 1966009 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.6053. Min Act: -0.1700
Data Index: 4278549 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.6053. Min Act: -0.1700
Data Index: 570135 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.5731. Min Act: -0.1700
Data Index: 2349705 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.5246. Min Act: -0.1700
Data Index: 570136 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.5085. Min Act: -0.1700
Data Index: 6026609 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.4598. Min Act: -0.1700
Data Index: 2310863 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.4273. Min Act: -0.1700
Data Index: 1853070 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.4273. Min Act: -0.1700
Data Index: 2147037 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3947. Min Act: -0.1700
Data Index: 5451901 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3947. Min Act: -0.1700
Data Index: 8320614 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3947. Min Act: -0.1700
Data Index: 6459173 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3783. Min Act: -0.1700
Data Index: 7399076 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3783. Min Act: -0.1700
Data Index: 2526290 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3783. Min Act: -0.1700
Data Index: 2975364 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3783. Min Act: -0.1700
Data Index: 692137 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3620. Min Act: -0.1700
Data Index: 6955272 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3620. Min Act: -0.1700
Data Index: 1919725 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3620. Min Act: -0.1700
Data Index: 433810 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7176. Min Range: -2.7176
Max Act: 2.3620. Min Act: -0.1700
Data Index: 3689543 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19