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

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

Neuron 3464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.2224. Min Act: -0.0001

Data Index: 692751 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.2279. Min Act: -0.0001

Data Index: 1345497 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1032984 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1152. Min Act: -0.0001

Data Index: 1052976 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0810. Min Act: -0.0001

Data Index: 103309 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0547. Min Act: -0.0001

Data Index: 562883 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0263. Min Act: -0.0001

Data Index: 125653 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9571. Min Act: -0.0001

Data Index: 817098 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9449. Min Act: -0.0001

Data Index: 1186808 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9823. Min Act: -0.0001

Data Index: 528778 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9945. Min Act: -0.0001

Data Index: 327997 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8756. Min Act: -0.0001

Data Index: 58536 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1168755 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9223. Min Act: -0.0001

Data Index: 632861 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8905. Min Act: -0.0001

Data Index: 1155923 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8878. Min Act: -0.0001

Data Index: 798508 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1197357 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8843. Min Act: -0.0001

Data Index: 248505 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1370 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1116488 (C4 (Web Text))

Max Activating Token Index: 486