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

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

Neuron 3277 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.6971. Min Act: -0.0000

Data Index: 1277056 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.4941. Min Act: -0.0000

Data Index: 11046 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.2806. Min Act: -0.0000

Data Index: 828107 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1255106 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.1059. Min Act: -0.0000

Data Index: 696370 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.0107. Min Act: -0.0000

Data Index: 66748 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1142685 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.6971. Min Range: -1.6971

Max Act: 1.0647. Min Act: -0.0000

Data Index: 685449 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9808. Min Act: -0.0000

Data Index: 649033 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9188. Min Act: -0.0000

Data Index: 148081 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9177. Min Act: -0.0000

Data Index: 432576 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8849. Min Act: -0.0000

Data Index: 829050 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1203845 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9298. Min Act: -0.0000

Data Index: 260131 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.9040. Min Act: -0.0000

Data Index: 631208 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1092754 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.7965. Min Act: -0.0000

Data Index: 271440 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8391. Min Act: -0.0000

Data Index: 351744 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1287450 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.6971. Min Range: -1.6971

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1058493 (C4 (Web Text))

Max Activating Token Index: 761