Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.7000. Min Act: -0.1700
Data Index: 1954805 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.5750. Min Act: -0.1700
Data Index: 6400855 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.5750. Min Act: -0.1700
Data Index: 7236620 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.5125. Min Act: -0.1700
Data Index: 1051060 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.5125. Min Act: -0.1700
Data Index: 8474005 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3562. Min Act: -0.1700
Data Index: 7215739 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1184324 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1776714 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3250. Min Act: -0.1700
Data Index: 6438273 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3250. Min Act: -0.1700
Data Index: 6591408 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.3250. Min Act: -0.1700
Data Index: 4877449 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2937. Min Act: -0.1700
Data Index: 2446745 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2937. Min Act: -0.1700
Data Index: 6334850 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2937. Min Act: -0.1700
Data Index: 5025804 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 4209409 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 2527533 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 6162016 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 7170478 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 6134883 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7000. Min Range: -5.7000
Max Act: 5.2625. Min Act: -0.1700
Data Index: 3244391 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19