Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.4696. Min Act: -0.1700
Data Index: 1490250 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.4696. Min Act: -0.1700
Data Index: 7825263 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.4696. Min Act: -0.1700
Data Index: 2601297 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.4071. Min Act: -0.1700
Data Index: 2137107 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.3134. Min Act: -0.1700
Data Index: 6027074 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2821. Min Act: -0.1700
Data Index: 4529883 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2509. Min Act: -0.1700
Data Index: 1187236 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2196. Min Act: -0.1700
Data Index: 6787509 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2196. Min Act: -0.1700
Data Index: 8693245 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2196. Min Act: -0.1700
Data Index: 6990359 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.2196. Min Act: -0.1700
Data Index: 3756483 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1884. Min Act: -0.1700
Data Index: 4023366 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1884. Min Act: -0.1700
Data Index: 7980009 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 7651183 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 2630834 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 4581051 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 1984901 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 8429160 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 244253 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4696. Min Range: -7.4696
Max Act: 7.1571. Min Act: -0.1700
Data Index: 4362874 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19