Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1404567 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1413707 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.3810. Min Act: -0.0000

Data Index: 531293 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.2481. Min Act: -0.0000

Data Index: 130743 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1800. Min Act: -0.0000

Data Index: 777377 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1296766 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1207252 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1023656 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.2019. Min Act: -0.0000

Data Index: 123416 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1652. Min Act: -0.0000

Data Index: 477168 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1571174 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1908. Min Act: -0.0000

Data Index: 566829 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1510. Min Act: -0.0000

Data Index: 60720 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1103. Min Act: -0.0000

Data Index: 407878 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1316. Min Act: -0.0000

Data Index: 626253 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1367. Min Act: -0.0000

Data Index: 267508 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1144. Min Act: -0.0000

Data Index: 268541 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.0467. Min Act: -0.0000

Data Index: 362943 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.1380. Min Act: -0.0000

Data Index: 678180 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.3810. Min Range: -1.3810

Max Act: 1.0694. Min Act: -0.0000

Data Index: 637228 (C4 (Web Text))

Max Activating Token Index: 337