Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2008. Min Range: -7.2008
Max Act: 7.2008. Min Act: -0.1700
Data Index: 8647374 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.9820. Min Act: -0.1700
Data Index: 6723845 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.9820. Min Act: -0.1700
Data Index: 7550086 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.9508. Min Act: -0.1700
Data Index: 1696557 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.8570. Min Act: -0.1700
Data Index: 7085310 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.8258. Min Act: -0.1700
Data Index: 2666321 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.8258. Min Act: -0.1700
Data Index: 6483410 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7633. Min Act: -0.1700
Data Index: 3090700 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7633. Min Act: -0.1700
Data Index: 6502855 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 1573337 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 4759645 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5565749 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.7008. Min Act: -0.1700
Data Index: 5931101 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.6070. Min Act: -0.1700
Data Index: 4056143 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.6070. Min Act: -0.1700
Data Index: 1015910 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.6070. Min Act: -0.1700
Data Index: 5758579 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2194562 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2549420 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.5758. Min Act: -0.1700
Data Index: 391204 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2008. Min Range: -7.2008
Max Act: 6.5758. Min Act: -0.1700
Data Index: 7296245 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19