Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1948 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.9224. Min Act: -0.0000

Data Index: 340553 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.8038. Min Act: -0.0000

Data Index: 582187 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7955. Min Act: -0.0000

Data Index: 135880 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7071. Min Act: -0.0000

Data Index: 30632 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7137. Min Act: -0.0000

Data Index: 172614 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6424. Min Act: -0.0000

Data Index: 165046 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6596. Min Act: -0.0000

Data Index: 474306 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6438. Min Act: -0.0000

Data Index: 111221 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6335. Min Act: -0.0000

Data Index: 400694 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6290. Min Act: -0.0000

Data Index: 867452 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6241. Min Act: -0.0000

Data Index: 394076 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1069702 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5732. Min Act: -0.0000

Data Index: 595920 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5238. Min Act: -0.0000

Data Index: 695310 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5751. Min Act: -0.0000

Data Index: 14604 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5497. Min Act: -0.0000

Data Index: 321917 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5482. Min Act: -0.0000

Data Index: 746647 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1034217 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5596. Min Act: -0.0000

Data Index: 729495 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1126788 (C4 (Web Text))

Max Activating Token Index: 494