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

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

Neuron 4620 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: 0.7723. Min Range: -0.7723

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1632268 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.7723. Min Act: -0.0000

Data Index: 36902 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6558. Min Act: -0.0000

Data Index: 168428 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6113. Min Act: -0.0000

Data Index: 727094 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6229. Min Act: -0.0000

Data Index: 949366 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6612. Min Act: -0.0000

Data Index: 75892 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1167992 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5830. Min Act: -0.0000

Data Index: 100714 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5201. Min Act: -0.0000

Data Index: 543327 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1296251 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5759. Min Act: -0.0000

Data Index: 17913 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5279. Min Act: -0.0000

Data Index: 534584 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5088. Min Act: -0.0000

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5444. Min Act: -0.0000

Data Index: 359347 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1345149 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1201949 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1230056 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5281. Min Act: -0.0000

Data Index: 153638 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.4747. Min Act: -0.0000

Data Index: 166707 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1299808 (C4 (Web Text))

Max Activating Token Index: 87