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

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

Neuron 5528 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1434. Min Range: -3.1434

Max Act: 3.1434. Min Act: -0.0000

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.9573. Min Act: -0.0000

Data Index: 891945 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1299818 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.6551. Min Act: -0.0000

Data Index: 940031 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.6024. Min Act: -0.0000

Data Index: 73994 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.5106. Min Act: -0.0000

Data Index: 1282039 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.4815. Min Act: -0.0000

Data Index: 300664 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.5950. Min Act: -0.0000

Data Index: 382070 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.5153. Min Act: -0.0000

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.4311. Min Act: -0.0000

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1358990 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.1199. Min Act: -0.0000

Data Index: 835232 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.3559. Min Act: -0.0000

Data Index: 227030 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.2255. Min Act: -0.0000

Data Index: 1131519 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.2177. Min Act: -0.0000

Data Index: 1253627 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.0697. Min Act: -0.0000

Data Index: 1625634 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.0931. Min Act: -0.0000

Data Index: 671852 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.1029. Min Act: -0.0000

Data Index: 731647 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.1783. Min Act: -0.0000

Data Index: 1310387 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.1434. Min Range: -3.1434

Max Act: 2.0514. Min Act: -0.0000

Data Index: 808363 (C4 (Web Text))

Max Activating Token Index: 776