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

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

Neuron 3444 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.5346. Min Act: -0.0000

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1615990 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4659. Min Act: -0.0000

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4739. Min Act: -0.0000

Data Index: 573510 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4524. Min Act: -0.0000

Data Index: 240137 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4470. Min Act: -0.0000

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4607. Min Act: -0.0000

Data Index: 144068 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4337. Min Act: -0.0000

Data Index: 253106 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4323. Min Act: -0.0000

Data Index: 5832 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4472. Min Act: -0.0000

Data Index: 502964 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4363. Min Act: -0.0000

Data Index: 774567 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4296. Min Act: -0.0000

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1636145 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1010947 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3578. Min Act: -0.0000

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4010. Min Act: -0.0000

Data Index: 387533 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4049. Min Act: -0.0000

Data Index: 417471 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4014. Min Act: -0.0000

Data Index: 44168 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1030015 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3960. Min Act: -0.0000

Data Index: 620559 (C4 (Web Text))

Max Activating Token Index: 736