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

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

Neuron 5984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.7952. Min Act: -0.0000

Data Index: 538534 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6572. Min Act: -0.0000

Data Index: 276049 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6329. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6379. Min Act: -0.0000

Data Index: 196278 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6011. Min Act: -0.0000

Data Index: 587195 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5797. Min Act: -0.0000

Data Index: 665384 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1244239 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5467. Min Act: -0.0000

Data Index: 872658 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1227280 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.4521. Min Act: -0.0000

Data Index: 639897 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3433. Min Act: -0.0000

Data Index: 843201 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3686. Min Act: -0.0000

Data Index: 75629 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3092. Min Act: -0.0000

Data Index: 286259 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3520. Min Act: -0.0000

Data Index: 375772 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1288840 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1517461 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.3190. Min Act: -0.0000

Data Index: 413025 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1647632 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1606020 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1617819 (Python Code)

Max Activating Token Index: 583