Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3335 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4793. Min Act: -0.0001

Data Index: 862846 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3960. Min Act: -0.0001

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4212. Min Act: -0.0001

Data Index: 1133032 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3763. Min Act: -0.0001

Data Index: 1192882 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3936. Min Act: -0.0001

Data Index: 226654 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1009428 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3991. Min Act: -0.0001

Data Index: 80030 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3602. Min Act: -0.0001

Data Index: 704418 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1248010 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3617. Min Act: -0.0001

Data Index: 1025162 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3600. Min Act: -0.0001

Data Index: 317206 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3507. Min Act: -0.0001

Data Index: 179171 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3878. Min Act: -0.0001

Data Index: 803892 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3292. Min Act: -0.0001

Data Index: 455575 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3464. Min Act: -0.0001

Data Index: 670488 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3228. Min Act: -0.0001

Data Index: 704248 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3532. Min Act: -0.0001

Data Index: 1039338 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3304. Min Act: -0.0001

Data Index: 823638 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3512. Min Act: -0.0001

Data Index: 631451 (C4 (Web Text))

Max Activating Token Index: 666