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

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

Neuron 4908 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7961. Min Act: -0.0000

Data Index: 665016 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1082942 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7598. Min Act: -0.0000

Data Index: 64287 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7222. Min Act: -0.0000

Data Index: 58292 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.7139. Min Act: -0.0000

Data Index: 959859 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6947. Min Act: -0.0000

Data Index: 313266 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6712. Min Act: -0.0000

Data Index: 377474 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6597. Min Act: -0.0000

Data Index: 502792 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6806. Min Act: -0.0000

Data Index: 317632 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6770. Min Act: -0.0000

Data Index: 500595 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6798. Min Act: -0.0000

Data Index: 373270 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6705. Min Act: -0.0000

Data Index: 43314 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6453. Min Act: -0.0000

Data Index: 42013 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6656. Min Act: -0.0000

Data Index: 412777 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6579. Min Act: -0.0000

Data Index: 601355 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6592. Min Act: -0.0000

Data Index: 930919 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6765. Min Act: -0.0000

Data Index: 438665 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6319. Min Act: -0.0000

Data Index: 840150 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6505. Min Act: -0.0000

Data Index: 713889 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.7961. Min Range: -0.7961

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1368251 (Python Code)

Max Activating Token Index: 6