Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.3247. Min Act: -0.1700
Data Index: 6179061 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.2935. Min Act: -0.1700
Data Index: 7239536 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.2310. Min Act: -0.1700
Data Index: 1003582 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1997. Min Act: -0.1700
Data Index: 5670626 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1372. Min Act: -0.1700
Data Index: 6435300 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1372. Min Act: -0.1700
Data Index: 7535447 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1372. Min Act: -0.1700
Data Index: 7535444 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1372. Min Act: -0.1700
Data Index: 8589420 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1372. Min Act: -0.1700
Data Index: 2406573 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1060. Min Act: -0.1700
Data Index: 4101732 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1060. Min Act: -0.1700
Data Index: 5670625 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 7535446 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 7535436 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 8183269 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0434. Min Act: -0.1700
Data Index: 5687614 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 1003596 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 6633484 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0747. Min Act: -0.1700
Data Index: 6619615 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.1060. Min Act: -0.1700
Data Index: 3823847 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3247. Min Range: -4.3247
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7535437 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19