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

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

Neuron 4734 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: 0.4845. Min Range: -0.4845

Max Act: 0.4845. Min Act: -0.0000

Data Index: 633401 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4832. Min Act: -0.0000

Data Index: 819478 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4595. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4516. Min Act: -0.0000

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4488. Min Act: -0.0000

Data Index: 27031 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4597. Min Act: -0.0000

Data Index: 959694 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1131201 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4295. Min Act: -0.0000

Data Index: 712177 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4414. Min Act: -0.0000

Data Index: 527567 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4032. Min Act: -0.0000

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1332173 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4160. Min Act: -0.0000

Data Index: 860888 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1304238 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4154. Min Act: -0.0000

Data Index: 653844 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.4112. Min Act: -0.0000

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1181574 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1262400 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3750. Min Act: -0.0000

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.4845. Min Range: -0.4845

Max Act: 0.3862. Min Act: -0.0000

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 347