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

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

Neuron 3086 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.2211. Min Act: -0.0000

Data Index: 566610 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1017214 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.1000. Min Act: 0.0000

Data Index: 468205 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0273. Min Act: -0.0000

Data Index: 563361 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.2211. Min Range: -1.2211

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1650499 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9319. Min Act: -0.0000

Data Index: 101819 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1297828 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9536. Min Act: -0.0000

Data Index: 208291 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9945. Min Act: -0.0000

Data Index: 782032 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9586. Min Act: -0.0000

Data Index: 733696 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1008981 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9827. Min Act: -0.0000

Data Index: 926457 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8893. Min Act: -0.0000

Data Index: 841300 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.9507. Min Act: -0.0000

Data Index: 598960 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8505. Min Act: -0.0000

Data Index: 659973 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8196. Min Act: 0.0000

Data Index: 224599 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.8146. Min Act: -0.0000

Data Index: 55370 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1632356 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.7874. Min Act: -0.0000

Data Index: 597408 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.2211. Min Range: -1.2211

Max Act: 0.7667. Min Act: -0.0000

Data Index: 804210 (C4 (Web Text))

Max Activating Token Index: 183