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

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

Neuron 3853 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: 1.6132. Min Range: -1.6132

Max Act: 1.5597. Min Act: -0.0001

Data Index: 164229 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.6132. Min Act: -0.0001

Data Index: 963676 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.5140. Min Act: -0.0001

Data Index: 784756 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.4244. Min Act: -0.0001

Data Index: 158039 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.4611. Min Act: -0.0001

Data Index: 355626 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.3996. Min Act: -0.0001

Data Index: 101481 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.3711. Min Act: -0.0001

Data Index: 510287 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.3614. Min Act: -0.0001

Data Index: 892631 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2848. Min Act: -0.0001

Data Index: 897907 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2755. Min Act: -0.0001

Data Index: 588480 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.3240. Min Act: -0.0001

Data Index: 269873 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2688. Min Act: -0.0001

Data Index: 526728 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2631. Min Act: -0.0001

Data Index: 922863 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2772. Min Act: -0.0001

Data Index: 693734 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2938. Min Act: -0.0001

Data Index: 1177955 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2203. Min Act: -0.0001

Data Index: 1182484 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2155. Min Act: -0.0001

Data Index: 496702 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.2316. Min Act: -0.0001

Data Index: 1591958 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.1682. Min Act: -0.0001

Data Index: 1363437 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.1037. Min Act: -0.0001

Data Index: 164461 (C4 (Web Text))

Max Activating Token Index: 998