Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.7192. Min Act: -0.1700
Data Index: 1322255 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.1567. Min Act: -0.1700
Data Index: 6224508 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.1567. Min Act: -0.1700
Data Index: 6378531 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.0942. Min Act: -0.1700
Data Index: 3156792 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.0317. Min Act: -0.1699
Data Index: 3392154 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7192. Min Range: -11.7192
Max Act: 11.0942. Min Act: -0.1700
Data Index: 5448202 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.9067. Min Act: -0.1700
Data Index: 3179170 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.9692. Min Act: -0.1699
Data Index: 5182854 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.9692. Min Act: -0.1700
Data Index: 2033800 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.9692. Min Act: -0.1700
Data Index: 3166971 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.8442. Min Act: -0.1700
Data Index: 8806942 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.8442. Min Act: -0.1700
Data Index: 6887304 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.8442. Min Act: -0.1700
Data Index: 432462 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.8442. Min Act: -0.1700
Data Index: 4037029 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.8442. Min Act: -0.1700
Data Index: 2106589 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.7817. Min Act: -0.1700
Data Index: 5188835 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.7817. Min Act: -0.1700
Data Index: 6339123 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.7192. Min Act: -0.1700
Data Index: 141253 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.7192. Min Act: -0.1700
Data Index: 8339772 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7192. Min Range: -11.7192
Max Act: 10.7192. Min Act: -0.1700
Data Index: 14647 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19