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

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

Neuron 6037 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: 2.8952. Min Range: -2.8952

Max Act: 2.8952. Min Act: -0.0000

Data Index: 1071186 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 2.8952. Min Range: -2.8952

Max Act: 2.4448. Min Act: -0.0000

Data Index: 1162352 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.8936. Min Act: -0.0000

Data Index: 299461 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.8658. Min Act: -0.0000

Data Index: 300402 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.7730. Min Act: -0.0000

Data Index: 1588428 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1448152 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5308. Min Act: -0.0000

Data Index: 564532 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5149. Min Act: -0.0000

Data Index: 22325 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.4167. Min Act: 0.0000

Data Index: 231719 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.5029. Min Act: -0.0000

Data Index: 44342 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.3025. Min Act: 0.0000

Data Index: 985012 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.4005. Min Act: -0.0000

Data Index: 90439 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.3501. Min Act: -0.0000

Data Index: 915246 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1542095 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1410101 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1345974 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.2761. Min Act: -0.0000

Data Index: 389177 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.2738. Min Act: -0.0000

Data Index: 334085 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1509593 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 2.8952. Min Range: -2.8952

Max Act: 1.1119. Min Act: -0.0000

Data Index: 111122 (C4 (Web Text))

Max Activating Token Index: 134