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

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

Neuron 4407 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: 0.8632. Min Range: -0.8632

Max Act: 0.8549. Min Act: 0.0000

Data Index: 66187 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8632. Min Act: -0.0000

Data Index: 119627 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.7812. Min Act: -0.0000

Data Index: 79512 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1212041 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6669. Min Act: -0.0000

Data Index: 476320 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6961. Min Act: -0.0000

Data Index: 912804 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5894. Min Act: -0.0000

Data Index: 393032 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1589154 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.6062. Min Act: -0.0000

Data Index: 814985 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5721. Min Act: -0.0000

Data Index: 838193 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5490. Min Act: -0.0000

Data Index: 422184 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1088861 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5289. Min Act: -0.0000

Data Index: 526257 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5192. Min Act: -0.0000

Data Index: 560706 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1409431 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1057652 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5254. Min Act: -0.0000

Data Index: 783390 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5341. Min Act: -0.0000

Data Index: 227478 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5202. Min Act: -0.0000

Data Index: 814976 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.5164. Min Act: -0.0000

Data Index: 500784 (C4 (Web Text))

Max Activating Token Index: 420