Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0247. Min Range: -7.0247
Max Act: 7.0247. Min Act: -0.1700
Data Index: 4856677 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.9310. Min Act: -0.1700
Data Index: 4870224 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.7747. Min Act: -0.1700
Data Index: 1647603 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.7122. Min Act: -0.1700
Data Index: 2121848 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.7122. Min Act: -0.1700
Data Index: 469628 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.6810. Min Act: -0.1700
Data Index: 3840008 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.6497. Min Act: -0.1700
Data Index: 1624392 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.6497. Min Act: -0.1700
Data Index: 960274 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.6185. Min Act: -0.1700
Data Index: 7049152 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.6185. Min Act: -0.1700
Data Index: 4942447 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5872. Min Act: -0.1700
Data Index: 687644 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5560. Min Act: -0.1700
Data Index: 2889282 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5560. Min Act: -0.1700
Data Index: 1453285 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5560. Min Act: -0.1700
Data Index: 3353154 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5247. Min Act: -0.1700
Data Index: 7374341 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5247. Min Act: -0.1700
Data Index: 96555 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.5247. Min Act: -0.1700
Data Index: 7354640 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.4935. Min Act: -0.1700
Data Index: 4073406 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.4622. Min Act: -0.1700
Data Index: 97835 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0247. Min Range: -7.0247
Max Act: 6.4935. Min Act: -0.1700
Data Index: 369774 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19