Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 247 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.4230. Min Act: -0.1700
Data Index: 8206377 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.3916. Min Act: -0.1700
Data Index: 6158987 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.3916. Min Act: -0.1700
Data Index: 254930 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.3132. Min Act: -0.1700
Data Index: 325852 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.3289. Min Act: -0.1700
Data Index: 3673022 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2975. Min Act: -0.1700
Data Index: 1821592 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2661. Min Act: -0.1700
Data Index: 4250340 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2346. Min Act: -0.1700
Data Index: 2366783 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2504. Min Act: -0.1700
Data Index: 4640426 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2504. Min Act: -0.1700
Data Index: 5119231 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2346. Min Act: -0.1700
Data Index: 6487369 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2346. Min Act: -0.1700
Data Index: 5417727 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 2212805 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 6251300 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 5048918 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 3837097 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 2957840 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2189. Min Act: -0.1700
Data Index: 2600375 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2032. Min Act: -0.1700
Data Index: 1045502 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4230. Min Range: -3.4230
Max Act: 3.2032. Min Act: -0.1700
Data Index: 7950368 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19