Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 47 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0128. Min Range: -1.0128

Max Act: 1.0128. Min Act: -0.0000

Data Index: 941064 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1078217 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7662. Min Act: -0.0000

Data Index: 410751 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.7218. Min Act: -0.0000

Data Index: 159037 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6812. Min Act: -0.0000

Data Index: 932504 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6348. Min Act: 0.0001

Data Index: 407571 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.6494. Min Act: 0.0000

Data Index: 401269 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.5513. Min Act: -0.0000

Data Index: 629310 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.5556. Min Act: -0.0000

Data Index: 137677 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.5170. Min Act: -0.0000

Data Index: 825051 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1551437 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4606. Min Act: 0.0001

Data Index: 1339365 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1529944 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4487. Min Act: 0.0001

Data Index: 39892 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.5159. Min Act: 0.0001

Data Index: 238030 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1610474 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4320. Min Act: -0.0000

Data Index: 537304 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4062. Min Act: 0.0000

Data Index: 40412 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4255. Min Act: -0.0000

Data Index: 429131 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.0128. Min Range: -1.0128

Max Act: 0.4218. Min Act: -0.0000

Data Index: 938660 (C4 (Web Text))

Max Activating Token Index: 626