Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1501 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.5452. Min Act: -0.0003

Data Index: 363042 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4609. Min Act: -0.0003

Data Index: 1181894 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4755. Min Act: -0.0004

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4334. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4203. Min Act: -0.0003

Data Index: 1575383 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3935. Min Act: -0.0004

Data Index: 629649 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3845. Min Act: -0.0003

Data Index: 1316686 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3744. Min Act: -0.0003

Data Index: 275940 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3569. Min Act: -0.0003

Data Index: 217814 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3442. Min Act: -0.0003

Data Index: 4099 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3528. Min Act: -0.0003

Data Index: 75310 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3282. Min Act: -0.0003

Data Index: 822263 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3263. Min Act: -0.0003

Data Index: 183386 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3446. Min Act: -0.0003

Data Index: 345058 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3091. Min Act: -0.0003

Data Index: 13618 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3157. Min Act: -0.0004

Data Index: 979480 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3125. Min Act: -0.0003

Data Index: 47077 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3067. Min Act: -0.0003

Data Index: 264437 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3075. Min Act: -0.0003

Data Index: 419381 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3064. Min Act: -0.0003

Data Index: 535450 (C4 (Web Text))

Max Activating Token Index: 496