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

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

Neuron 1560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.6952. Min Act: -0.0002

Data Index: 1375482 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.4071. Min Act: -0.0002

Data Index: 1613442 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.3891. Min Act: -0.0002

Data Index: 374778 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.4055. Min Act: -0.0002

Data Index: 952641 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.3921. Min Act: -0.0002

Data Index: 1126659 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.3573. Min Act: -0.0002

Data Index: 826595 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.3376. Min Act: -0.0002

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.3613. Min Act: -0.0002

Data Index: 1223202 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2326. Min Act: -0.0002

Data Index: 1028598 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2948. Min Act: -0.0002

Data Index: 305650 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2362. Min Act: -0.0002

Data Index: 509229 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2036. Min Act: -0.0002

Data Index: 586641 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.1912. Min Act: -0.0002

Data Index: 1437154 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2120. Min Act: -0.0002

Data Index: 550180 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2030. Min Act: -0.0002

Data Index: 318107 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.1628. Min Act: -0.0002

Data Index: 921711 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2207. Min Act: -0.0002

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.2380. Min Act: -0.0002

Data Index: 1021837 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.1498. Min Act: -0.0002

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.6952. Min Range: -1.6952

Max Act: 1.1413. Min Act: -0.0002

Data Index: 238852 (C4 (Web Text))

Max Activating Token Index: 474