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

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

Neuron 5097 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: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0000

Data Index: 396552 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7501. Min Act: -0.0000

Data Index: 504251 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6571. Min Act: -0.0000

Data Index: 962040 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7265. Min Act: -0.0000

Data Index: 2012 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1169546 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5614. Min Act: -0.0000

Data Index: 723761 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5603. Min Act: -0.0000

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5518. Min Act: -0.0000

Data Index: 674641 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5490. Min Act: -0.0000

Data Index: 297344 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5516. Min Act: -0.0000

Data Index: 428311 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5172. Min Act: -0.0000

Data Index: 599344 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1130409 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1594029 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5147. Min Act: -0.0000

Data Index: 395096 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4766. Min Act: -0.0000

Data Index: 194986 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1316097 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4599. Min Act: -0.0000

Data Index: 513827 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1489362 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4937. Min Act: -0.0000

Data Index: 301642 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.4534. Min Act: -0.0000

Data Index: 836318 (C4 (Web Text))

Max Activating Token Index: 935