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

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

Neuron 3213 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2671. Min Range: -2.2671

Max Act: 2.2671. Min Act: -0.0000

Data Index: 286276 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.2671. Min Range: -2.2671

Max Act: 2.2204. Min Act: -0.0000

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 2.2671. Min Range: -2.2671

Max Act: 2.0675. Min Act: -0.0000

Data Index: 1408036 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.9217. Min Act: -0.0000

Data Index: 116573 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.9182. Min Act: -0.0000

Data Index: 893678 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1480761 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.8117. Min Act: -0.0000

Data Index: 552006 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.7982. Min Act: -0.0000

Data Index: 602399 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.7453. Min Act: -0.0000

Data Index: 47673 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1634485 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.6934. Min Act: -0.0000

Data Index: 98406 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.5566. Min Act: -0.0000

Data Index: 666264 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.7213. Min Act: -0.0000

Data Index: 255574 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.7163. Min Act: -0.0000

Data Index: 1019061 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1014764 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1401803 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.5417. Min Act: -0.0000

Data Index: 372501 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.5304. Min Act: -0.0000

Data Index: 227497 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.4161. Min Act: -0.0000

Data Index: 386516 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.2671. Min Range: -2.2671

Max Act: 1.5082. Min Act: -0.0000

Data Index: 947427 (C4 (Web Text))

Max Activating Token Index: 605