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

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

Neuron 4793 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.7417. Min Act: 0.0000

Data Index: 607832 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6816. Min Act: -0.0000

Data Index: 141588 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.6402. Min Act: -0.0000

Data Index: 773106 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5865. Min Act: -0.0000

Data Index: 340537 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5565. Min Act: -0.0000

Data Index: 612050 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1260089 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5527. Min Act: -0.0000

Data Index: 590780 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5263. Min Act: -0.0000

Data Index: 790633 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4945. Min Act: -0.0000

Data Index: 769145 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4424. Min Act: -0.0000

Data Index: 814595 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1076994 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4862. Min Act: -0.0000

Data Index: 292018 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4742. Min Act: -0.0000

Data Index: 933101 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1591183 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4518. Min Act: -0.0000

Data Index: 420650 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1202956 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4426. Min Act: -0.0000

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4352. Min Act: -0.0000

Data Index: 918659 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1428995 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.7417. Min Range: -0.7417

Max Act: 0.4350. Min Act: -0.0000

Data Index: 960057 (C4 (Web Text))

Max Activating Token Index: 245