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

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

Neuron 4526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.6144. Min Act: -0.0000

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.2549. Min Act: -0.0000

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.3768. Min Act: -0.0000

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.1728. Min Act: -0.0000

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.2967. Min Act: -0.0000

Data Index: 714296 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.2231. Min Act: -0.0000

Data Index: 546229 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.1714. Min Act: -0.0000

Data Index: 413778 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.1417. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.1884. Min Act: -0.0000

Data Index: 115109 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.9428. Min Act: -0.0000

Data Index: 233189 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.9154. Min Act: -0.0000

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.0422. Min Act: -0.0000

Data Index: 1153521 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 4.6144. Min Range: -4.6144

Max Act: 4.0340. Min Act: -0.0000

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.8637. Min Act: -0.0000

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.8124. Min Act: -0.0000

Data Index: 906519 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.7593. Min Act: -0.0000

Data Index: 426332 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.9296. Min Act: -0.0000

Data Index: 648399 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.5657. Min Act: -0.0000

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.7111. Min Act: 0.0000

Data Index: 309272 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 4.6144. Min Range: -4.6144

Max Act: 3.4869. Min Act: -0.0000

Data Index: 852346 (C4 (Web Text))

Max Activating Token Index: 639