Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0441. Min Range: -8.0441
Max Act: 8.0441. Min Act: -0.1700
Data Index: 5569088 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.9191. Min Act: -0.1700
Data Index: 8476229 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.8566. Min Act: -0.1700
Data Index: 3619743 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.8566. Min Act: -0.1700
Data Index: 674821 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.8566. Min Act: -0.1700
Data Index: 1294797 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7941. Min Act: -0.1700
Data Index: 6689330 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7941. Min Act: -0.1700
Data Index: 7081986 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7316. Min Act: -0.1700
Data Index: 8002429 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7316. Min Act: -0.1700
Data Index: 8482430 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7316. Min Act: -0.1700
Data Index: 3972862 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.7316. Min Act: -0.1700
Data Index: 8179589 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.6691. Min Act: -0.1700
Data Index: 8596198 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.6691. Min Act: -0.1700
Data Index: 2899764 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.6066. Min Act: -0.1700
Data Index: 1909051 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 1719286 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.6066. Min Act: -0.1700
Data Index: 885494 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 2172178 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.6066. Min Act: -0.1700
Data Index: 6655432 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 8126691 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0441. Min Range: -8.0441
Max Act: 7.5441. Min Act: -0.1700
Data Index: 2706817 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19