Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 3501576 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.6600. Min Act: -0.1700
Data Index: 2383095 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5975. Min Act: -0.1700
Data Index: 8543330 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5350. Min Act: -0.1700
Data Index: 680203 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5350. Min Act: -0.1700
Data Index: 780135 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 6793762 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 8317710 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 5405783 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 2052824 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 1203533 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3475. Min Act: -0.1700
Data Index: 3977815 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7526729 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 3629234 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7420500 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 4224121 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7991886 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 1461623 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 2662840 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 8560132 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 8583588 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19