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

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

Neuron 3716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1056389 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8897. Min Act: -0.0000

Data Index: 262402 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5746. Min Act: -0.0000

Data Index: 762757 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1034126 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5400. Min Act: -0.0000

Data Index: 781867 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5185. Min Act: -0.0000

Data Index: 91119 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5871. Min Act: -0.0000

Data Index: 149980 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4067. Min Act: -0.0001

Data Index: 1211361 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5162. Min Act: -0.0000

Data Index: 863993 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5031. Min Act: -0.0000

Data Index: 700685 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4657. Min Act: -0.0000

Data Index: 562177 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4542. Min Act: -0.0000

Data Index: 510181 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3223. Min Act: -0.0000

Data Index: 459032 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3751. Min Act: -0.0000

Data Index: 549014 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3613. Min Act: -0.0000

Data Index: 921928 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2940. Min Act: -0.0000

Data Index: 229818 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2046. Min Act: -0.0000

Data Index: 421476 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2429. Min Act: -0.0000

Data Index: 896180 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2699. Min Act: -0.0001

Data Index: 697600 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1174466 (C4 (Web Text))

Max Activating Token Index: 901