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

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

Neuron 3067 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2705. Min Act: -0.0000

Data Index: 651878 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2201. Min Act: -0.0000

Data Index: 558362 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1269204 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2159. Min Act: -0.0000

Data Index: 501338 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2092. Min Act: -0.0000

Data Index: 864012 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1981. Min Act: -0.0000

Data Index: 572316 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1981. Min Act: -0.0000

Data Index: 786430 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1006613 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1815. Min Act: -0.0000

Data Index: 697810 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1920. Min Act: -0.0000

Data Index: 619686 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1777. Min Act: -0.0000

Data Index: 123728 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1806. Min Act: -0.0000

Data Index: 44029 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1802. Min Act: -0.0000

Data Index: 5204 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1768. Min Act: -0.0000

Data Index: 905511 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1760. Min Act: -0.0000

Data Index: 546014 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1733. Min Act: -0.0000

Data Index: 911360 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1224168 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1712. Min Act: -0.0000

Data Index: 881772 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1319071 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1627. Min Act: -0.0000

Data Index: 762263 (C4 (Web Text))

Max Activating Token Index: 647