Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4843 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.7216. Min Act: -0.0000

Data Index: 510942 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.6210. Min Act: -0.0000

Data Index: 1321927 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.6218. Min Act: -0.0000

Data Index: 11622 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.7710. Min Act: -0.0000

Data Index: 865212 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.4101. Min Act: -0.0000

Data Index: 862148 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.3916. Min Act: -0.0000

Data Index: 1213739 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.4884. Min Act: -0.0000

Data Index: 226519 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1145494 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.2826. Min Act: -0.0000

Data Index: 40636 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.2543. Min Act: -0.0000

Data Index: 191290 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.4884. Min Act: -0.0000

Data Index: 1313049 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.3288. Min Act: -0.0000

Data Index: 340929 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.1233. Min Act: -0.0000

Data Index: 1291249 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.2413. Min Act: -0.0000

Data Index: 731501 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.2106. Min Act: -0.0001

Data Index: 282847 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.0982. Min Act: -0.0000

Data Index: 1320735 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.1956. Min Act: -0.0000

Data Index: 850120 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1167381 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.0174. Min Act: -0.0000

Data Index: 392948 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.7710. Min Range: -2.7710

Max Act: 2.1129. Min Act: -0.0000

Data Index: 1078067 (C4 (Web Text))

Max Activating Token Index: 390