Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1599. Min Range: -6.1599

Max Act: 6.1599. Min Act: -0.0000

Data Index: 843797 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 6.1599. Min Range: -6.1599

Max Act: 4.4427. Min Act: -0.0000

Data Index: 919046 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 6.1599. Min Range: -6.1599

Max Act: 4.2282. Min Act: -0.0000

Data Index: 165219 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.8809. Min Act: -0.0000

Data Index: 914724 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5497. Min Act: -0.0000

Data Index: 659384 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.7783. Min Act: -0.0000

Data Index: 1026871 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.3086. Min Act: -0.0000

Data Index: 499906 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.4467. Min Act: -0.0000

Data Index: 716337 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5617. Min Act: -0.0000

Data Index: 948534 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.4930. Min Act: -0.0000

Data Index: 154176 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5857. Min Act: -0.0000

Data Index: 701438 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5714. Min Act: -0.0000

Data Index: 990094 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.2592. Min Act: -0.0000

Data Index: 421109 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5580. Min Act: -0.0000

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1316043 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.3096. Min Act: -0.0000

Data Index: 912930 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.4473. Min Act: -0.0001

Data Index: 727355 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.4518. Min Act: -0.0000

Data Index: 210784 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.4354. Min Act: -0.0000

Data Index: 121167 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 6.1599. Min Range: -6.1599

Max Act: 3.5792. Min Act: -0.0000

Data Index: 86904 (C4 (Web Text))

Max Activating Token Index: 338