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

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

Neuron 1742 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0002

Data Index: 1057511 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4617. Min Act: -0.0001

Data Index: 955052 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4417. Min Act: -0.0002

Data Index: 909516 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3605. Min Act: -0.0002

Data Index: 66055 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3169. Min Act: -0.0002

Data Index: 774921 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2627. Min Act: -0.0002

Data Index: 1143377 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2949. Min Act: -0.0002

Data Index: 1325871 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2662. Min Act: -0.0002

Data Index: 99392 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2446. Min Act: -0.0002

Data Index: 422064 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2649. Min Act: -0.0001

Data Index: 337037 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2576. Min Act: -0.0002

Data Index: 1042206 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2046. Min Act: -0.0002

Data Index: 1036445 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1942. Min Act: -0.0002

Data Index: 32167 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2219. Min Act: -0.0001

Data Index: 881924 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2206. Min Act: -0.0001

Data Index: 1210736 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1883. Min Act: -0.0001

Data Index: 1250007 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0674. Min Act: -0.0002

Data Index: 951104 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2031. Min Act: -0.0002

Data Index: 1260893 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1188024 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1688. Min Act: -0.0001

Data Index: 1342822 (C4 (Web Text))

Max Activating Token Index: 77