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

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

Neuron 3379 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: 1.1494. Min Range: -1.1494

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1171572 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.1494. Min Range: -1.1494

Max Act: 1.0446. Min Act: -0.0001

Data Index: 688311 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.1494. Min Range: -1.1494

Max Act: 1.0376. Min Act: -0.0001

Data Index: 138462 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8320. Min Act: -0.0001

Data Index: 681113 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9764. Min Act: -0.0001

Data Index: 109189 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9773. Min Act: -0.0001

Data Index: 57784 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1200967 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1346719 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9715. Min Act: -0.0001

Data Index: 536981 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9419. Min Act: -0.0001

Data Index: 572008 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9397. Min Act: -0.0001

Data Index: 7329 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.9075. Min Act: -0.0001

Data Index: 965811 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8541. Min Act: -0.0001

Data Index: 184436 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.7980. Min Act: -0.0001

Data Index: 1534401 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1270589 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1170020 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8812. Min Act: -0.0001

Data Index: 226333 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1018623 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8390. Min Act: -0.0001

Data Index: 850944 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.1494. Min Range: -1.1494

Max Act: 0.8799. Min Act: -0.0001

Data Index: 269368 (C4 (Web Text))

Max Activating Token Index: 927