Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.5675. Min Act: -0.1700
Data Index: 1141034 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.3800. Min Act: -0.1700
Data Index: 4357485 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.3175. Min Act: -0.1700
Data Index: 871262 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.3175. Min Act: -0.1700
Data Index: 6977775 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.3175. Min Act: -0.1700
Data Index: 3427697 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.2550. Min Act: -0.1700
Data Index: 2709974 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.2550. Min Act: -0.1700
Data Index: 7226998 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.2550. Min Act: -0.1700
Data Index: 7549066 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.2550. Min Act: -0.1700
Data Index: 4503990 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1925. Min Act: -0.1700
Data Index: 1896006 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1925. Min Act: -0.1700
Data Index: 7660112 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1925. Min Act: -0.1700
Data Index: 3259618 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1925. Min Act: -0.1700
Data Index: 5483245 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 4031517 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 5762985 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 8788452 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 7712128 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 5067268 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1925. Min Act: -0.1700
Data Index: 8543574 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5675. Min Range: -8.5675
Max Act: 8.1300. Min Act: -0.1700
Data Index: 4765567 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19