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

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

Neuron 3221 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: 3.3032. Min Range: -3.3032

Max Act: 3.3032. Min Act: -0.0000

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.2896. Min Act: -0.0000

Data Index: 333077 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.1262. Min Act: -0.0000

Data Index: 807836 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0403. Min Act: -0.0000

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.7579. Min Act: -0.0001

Data Index: 160965 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.7421. Min Act: -0.0000

Data Index: 501910 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.6837. Min Act: -0.0000

Data Index: 299562 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.6962. Min Act: -0.0000

Data Index: 518707 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.6882. Min Act: -0.0000

Data Index: 1108772 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.4827. Min Act: -0.0000

Data Index: 121467 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.4658. Min Act: -0.0000

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.4725. Min Act: -0.0000

Data Index: 1292144 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.6735. Min Act: -0.0000

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.3688. Min Act: -0.0000

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.2141. Min Act: -0.0000

Data Index: 647015 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.4541. Min Act: -0.0000

Data Index: 376743 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.5634. Min Act: -0.0001

Data Index: 263061 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.4135. Min Act: -0.0001

Data Index: 608575 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.5223. Min Act: -0.0000

Data Index: 1076578 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.2089. Min Act: -0.0000

Data Index: 1060626 (C4 (Web Text))

Max Activating Token Index: 891