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

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

Neuron 323 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4196. Min Range: -9.4196

Max Act: 9.4196. Min Act: -0.0000

Data Index: 809294 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 9.4196. Min Range: -9.4196

Max Act: 9.3769. Min Act: -0.0000

Data Index: 714367 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.9648. Min Act: -0.0000

Data Index: 505397 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.6805. Min Act: -0.0000

Data Index: 358914 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.8189. Min Act: -0.0000

Data Index: 435655 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.3627. Min Act: -0.0000

Data Index: 548095 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.9425. Min Act: -0.0000

Data Index: 1346721 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.0935. Min Act: -0.0000

Data Index: 700835 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.1194. Min Act: -0.0000

Data Index: 1072801 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.1058. Min Act: -0.0000

Data Index: 126603 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.2067. Min Act: -0.0000

Data Index: 796788 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.0117. Min Act: -0.0000

Data Index: 306029 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 9.4196. Min Range: -9.4196

Max Act: 8.1400. Min Act: -0.0000

Data Index: 383958 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.9255. Min Act: -0.0000

Data Index: 388687 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.6859. Min Act: -0.0000

Data Index: 572397 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.8204. Min Act: -0.0000

Data Index: 1068600 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.7978. Min Act: -0.0000

Data Index: 136204 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.4177. Min Act: -0.0000

Data Index: 1301695 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.8885. Min Act: -0.0000

Data Index: 915385 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 9.4196. Min Range: -9.4196

Max Act: 7.6917. Min Act: -0.0000

Data Index: 1214480 (C4 (Web Text))

Max Activating Token Index: 548