Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1753 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.5291. Min Act: -0.1700
Data Index: 116235 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.5129. Min Act: -0.1700
Data Index: 8421016 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.5291. Min Act: -0.1700
Data Index: 820770 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4805. Min Act: -0.1700
Data Index: 1028895 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4480. Min Act: -0.1700
Data Index: 4182433 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4317. Min Act: -0.1700
Data Index: 2298226 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4317. Min Act: -0.1700
Data Index: 2494119 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4317. Min Act: -0.1700
Data Index: 5568980 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3991. Min Act: -0.1700
Data Index: 1135881 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.4154. Min Act: -0.1700
Data Index: 4667119 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3828. Min Act: -0.1700
Data Index: 989618 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3991. Min Act: -0.1700
Data Index: 7500660 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3991. Min Act: -0.1700
Data Index: 3541327 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3501. Min Act: -0.1700
Data Index: 8512868 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3828. Min Act: -0.1700
Data Index: 5396354 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3828. Min Act: -0.1700
Data Index: 3579197 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3664. Min Act: -0.1700
Data Index: 6911540 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3664. Min Act: -0.1700
Data Index: 1564898 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3664. Min Act: -0.1700
Data Index: 6697705 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5291. Min Range: -2.5291
Max Act: 2.3991. Min Act: -0.1700
Data Index: 6938271 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19