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

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

Neuron 3635 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: 1.0616. Min Range: -1.0616

Max Act: 1.0616. Min Act: -0.0001

Data Index: 203112 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9590. Min Act: -0.0001

Data Index: 267280 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1300014 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8238. Min Act: -0.0001

Data Index: 62611 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6824. Min Act: -0.0001

Data Index: 1135087 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8895. Min Act: -0.0001

Data Index: 1207573 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8659. Min Act: -0.0001

Data Index: 1079372 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8225. Min Act: -0.0001

Data Index: 153875 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7611. Min Act: -0.0001

Data Index: 360555 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8074. Min Act: -0.0001

Data Index: 819252 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1267873 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7715. Min Act: -0.0001

Data Index: 111139 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7657. Min Act: -0.0001

Data Index: 1204889 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1091849 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7099. Min Act: -0.0001

Data Index: 598436 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7403. Min Act: -0.0001

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7037. Min Act: -0.0001

Data Index: 431805 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1224465 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6563. Min Act: -0.0001

Data Index: 772164 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.6512. Min Act: -0.0001

Data Index: 908241 (C4 (Web Text))

Max Activating Token Index: 555