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

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

Neuron 138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.3256. Min Act: -0.0001

Data Index: 1326704 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.4053. Min Act: -0.0001

Data Index: 1272755 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.3234. Min Act: -0.0001

Data Index: 624900 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.3614. Min Act: -0.0001

Data Index: 414851 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.2126. Min Act: -0.0001

Data Index: 1180386 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1833. Min Act: -0.0001

Data Index: 753719 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1782. Min Act: -0.0001

Data Index: 198218 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1302. Min Act: -0.0001

Data Index: 802115 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0383. Min Act: -0.0001

Data Index: 706600 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1695. Min Act: -0.0001

Data Index: 890909 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1611. Min Act: -0.0001

Data Index: 39199 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1783. Min Act: -0.0001

Data Index: 510389 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.2076. Min Act: -0.0001

Data Index: 934125 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.2154. Min Act: -0.0001

Data Index: 1214150 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1104. Min Act: -0.0001

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1302. Min Act: -0.0001

Data Index: 512080 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1315359 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0824. Min Act: -0.0001

Data Index: 1242608 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0298. Min Act: -0.0001

Data Index: 1279156 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.4053. Min Range: -1.4053

Max Act: 1.0453. Min Act: -0.0001

Data Index: 994668 (C4 (Web Text))

Max Activating Token Index: 705