Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3727 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2545. Min Act: -0.0001

Data Index: 60532 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.1689. Min Act: -0.0001

Data Index: 448590 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2411. Min Act: -0.0001

Data Index: 1231082 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2101. Min Act: -0.0001

Data Index: 1067972 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.1172. Min Act: -0.0001

Data Index: 1319506 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2204. Min Act: -0.0001

Data Index: 1104754 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2308. Min Act: -0.0001

Data Index: 1252446 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.1458. Min Act: -0.0001

Data Index: 538239 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0713. Min Act: -0.0001

Data Index: 18831 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0697. Min Act: -0.0001

Data Index: 1167729 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1334366 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0680. Min Act: -0.0001

Data Index: 866754 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9869. Min Act: -0.0001

Data Index: 844233 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0695. Min Act: -0.0001

Data Index: 1084553 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0588. Min Act: -0.0001

Data Index: 711502 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0267. Min Act: -0.0001

Data Index: 51081 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1242215 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0581. Min Act: -0.0001

Data Index: 1228872 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0865. Min Act: -0.0001

Data Index: 509993 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0491. Min Act: -0.0001

Data Index: 628326 (C4 (Web Text))

Max Activating Token Index: 69