Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.2009. Min Act: -0.1700
Data Index: 1142024 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.2009. Min Act: -0.1700
Data Index: 154764 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1676. Min Act: -0.1700
Data Index: 8122017 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1176. Min Act: -0.1700
Data Index: 2366808 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1176. Min Act: -0.1700
Data Index: 4340840 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1176. Min Act: -0.1700
Data Index: 3482355 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1008. Min Act: -0.1700
Data Index: 2994281 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1008. Min Act: -0.1700
Data Index: 4114795 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1008. Min Act: -0.1700
Data Index: 4719337 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1176. Min Act: -0.1700
Data Index: 2736357 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1008. Min Act: -0.1700
Data Index: 4751413 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.1008. Min Act: -0.1699
Data Index: 4390761 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0841. Min Act: -0.1700
Data Index: 3234134 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0673. Min Act: -0.1700
Data Index: 1855144 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0841. Min Act: -0.1700
Data Index: 4097719 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0673. Min Act: -0.1700
Data Index: 4359062 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0505. Min Act: -0.1700
Data Index: 8075769 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0505. Min Act: -0.1700
Data Index: 1350942 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0168. Min Act: -0.1700
Data Index: 8631950 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2009. Min Range: -2.2009
Max Act: 2.0337. Min Act: -0.1700
Data Index: 5590457 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19