Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0740. Min Range: -6.0740
Max Act: 6.0740. Min Act: -0.1700
Data Index: 6873042 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0740. Min Range: -6.0740
Max Act: 6.0115. Min Act: -0.1700
Data Index: 1979580 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.9802. Min Act: -0.1700
Data Index: 618139 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.9490. Min Act: -0.1700
Data Index: 503685 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7927. Min Act: -0.1700
Data Index: 700616 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5153852 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5577066 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7615. Min Act: -0.1700
Data Index: 4601133 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7302. Min Act: -0.1700
Data Index: 1736215 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.7302. Min Act: -0.1700
Data Index: 8738157 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6990. Min Act: -0.1700
Data Index: 5196259 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6990. Min Act: -0.1700
Data Index: 7578023 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6990. Min Act: -0.1700
Data Index: 809971 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1113125 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6990. Min Act: -0.1700
Data Index: 7151814 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3226150 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1942649 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6677. Min Act: -0.1700
Data Index: 5614335 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3745270 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0740. Min Range: -6.0740
Max Act: 5.5740. Min Act: -0.1700
Data Index: 7535089 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19