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

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

Neuron 5055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1270151 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1316917 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2059. Min Act: -0.0000

Data Index: 120667 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2084. Min Act: -0.0000

Data Index: 881410 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2051. Min Act: -0.0000

Data Index: 21053 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.2046. Min Act: -0.0000

Data Index: 867825 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1235552 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1763. Min Act: -0.0000

Data Index: 389689 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1048100 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1811. Min Act: -0.0000

Data Index: 221767 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1745. Min Act: -0.0000

Data Index: 606733 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1789. Min Act: -0.0000

Data Index: 48060 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1103497 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1250317 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1578. Min Act: -0.0000

Data Index: 341678 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1552. Min Act: -0.0000

Data Index: 106196 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1565. Min Act: -0.0000

Data Index: 943266 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1408. Min Act: -0.0000

Data Index: 449454 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1487. Min Act: -0.0000

Data Index: 174259 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.2422. Min Range: -0.2422

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1169341 (C4 (Web Text))

Max Activating Token Index: 588