Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.7522. Min Act: -0.1700
Data Index: 8055029 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.6584. Min Act: -0.1700
Data Index: 8147487 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.5022. Min Act: -0.1700
Data Index: 6601453 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.3147. Min Act: -0.1700
Data Index: 2078250 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.3147. Min Act: -0.1700
Data Index: 8791780 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.2834. Min Act: -0.1700
Data Index: 1342847 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.2522. Min Act: -0.1700
Data Index: 4278903 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.2209. Min Act: -0.1700
Data Index: 6381879 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1584. Min Act: -0.1700
Data Index: 1105149 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1584. Min Act: -0.1700
Data Index: 2792080 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1584. Min Act: -0.1700
Data Index: 684625 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1584. Min Act: -0.1700
Data Index: 4899674 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1584. Min Act: -0.1700
Data Index: 940696 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1272. Min Act: -0.1700
Data Index: 8225525 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.1272. Min Act: -0.1700
Data Index: 1733240 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.0959. Min Act: -0.1700
Data Index: 5724070 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.0959. Min Act: -0.1700
Data Index: 3575770 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.0959. Min Act: -0.1700
Data Index: 3331636 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.0959. Min Act: -0.1700
Data Index: 2151655 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7522. Min Range: -5.7522
Max Act: 5.0959. Min Act: -0.1700
Data Index: 8053698 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19