Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2857 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.9271. Min Act: 0.0001

Data Index: 1120771 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1274735 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8519. Min Act: -0.0000

Data Index: 764600 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8902. Min Act: -0.0000

Data Index: 644308 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8540. Min Act: -0.0000

Data Index: 640085 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1184234 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8016. Min Act: -0.0000

Data Index: 172910 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1112655 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8401. Min Act: -0.0000

Data Index: 211551 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7877. Min Act: 0.0000

Data Index: 1135297 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1210415 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7242. Min Act: 0.0000

Data Index: 81912 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7742. Min Act: 0.0000

Data Index: 409803 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1189048 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7678. Min Act: -0.0000

Data Index: 689325 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7661. Min Act: -0.0000

Data Index: 220116 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7055. Min Act: -0.0000

Data Index: 314248 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1057778 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7179. Min Act: -0.0000

Data Index: 811372 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7129. Min Act: -0.0000

Data Index: 666620 (C4 (Web Text))

Max Activating Token Index: 152