Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1669 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0001

Data Index: 240636 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2712. Min Act: -0.0001

Data Index: 38315 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1181368 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1276626 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2537. Min Act: -0.0001

Data Index: 790759 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2457. Min Act: -0.0001

Data Index: 788304 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1443350 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2635. Min Act: -0.0001

Data Index: 995878 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1622336 (Python Code)

Max Activating Token Index: 304

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2410. Min Act: -0.0001

Data Index: 277658 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1490820 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1231767 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1269474 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1013057 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2276. Min Act: -0.0001

Data Index: 377055 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2504. Min Act: -0.0001

Data Index: 750243 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1372759 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2315. Min Act: -0.0001

Data Index: 918913 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1538468 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1296998 (C4 (Web Text))

Max Activating Token Index: 60