Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 68 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.6144. Min Act: -0.0001

Data Index: 14179 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.6193. Min Act: -0.0000

Data Index: 65887 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5779. Min Act: -0.0001

Data Index: 178016 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5531. Min Act: -0.0001

Data Index: 669270 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.5268. Min Act: -0.0000

Data Index: 909430 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4257. Min Act: -0.0000

Data Index: 536334 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4833. Min Act: -0.0001

Data Index: 580181 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4446. Min Act: -0.0001

Data Index: 783825 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4287. Min Act: -0.0000

Data Index: 580743 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1085578 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4090. Min Act: -0.0001

Data Index: 671012 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4364. Min Act: -0.0001

Data Index: 641918 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4189. Min Act: -0.0000

Data Index: 246213 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4476. Min Act: -0.0000

Data Index: 64521 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1345375 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1128186 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4044. Min Act: -0.0001

Data Index: 519323 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4454. Min Act: -0.0000

Data Index: 394377 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.6193. Min Range: -0.6193

Max Act: 0.4157. Min Act: -0.0000

Data Index: 965018 (C4 (Web Text))

Max Activating Token Index: 53