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

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

Neuron 4732 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.8665. Min Act: -0.0001

Data Index: 3650 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6580. Min Act: -0.0001

Data Index: 441283 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4841. Min Act: -0.0001

Data Index: 1223581 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.6406. Min Act: -0.0001

Data Index: 476917 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4950. Min Act: -0.0001

Data Index: 1344913 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1195043 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4317. Min Act: -0.0001

Data Index: 747076 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4316. Min Act: -0.0001

Data Index: 104512 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.3929. Min Act: -0.0001

Data Index: 348852 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4076. Min Act: -0.0001

Data Index: 1321211 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.4091. Min Act: -0.0000

Data Index: 160172 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.3046. Min Act: -0.0001

Data Index: 249532 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.2780. Min Act: -0.0001

Data Index: 1355188 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.3343. Min Act: -0.0001

Data Index: 400429 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.3623. Min Act: -0.0001

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.1707. Min Act: -0.0001

Data Index: 1118157 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.2449. Min Act: -0.0001

Data Index: 728017 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.1825. Min Act: -0.0001

Data Index: 1126438 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.2948. Min Act: -0.0001

Data Index: 1270698 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.8665. Min Range: -1.8665

Max Act: 1.2901. Min Act: -0.0001

Data Index: 565425 (C4 (Web Text))

Max Activating Token Index: 99