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

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

Neuron 2038 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: 1.5346. Min Range: -1.5346

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1365529 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1551831 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1555139 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1504695 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1271361 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1455071 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1498703 (Python Code)

Max Activating Token Index: 886

Text #7

Max Range: 1.5346. Min Range: -1.5346

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1557998 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1596553 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8892. Min Act: -0.0000

Data Index: 487375 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1575160 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8960. Min Act: -0.0000

Data Index: 329837 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1566986 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1238530 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1028138 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1153549 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1472694 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1632866 (Python Code)

Max Activating Token Index: 545

Text #18

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1613504 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 1.5346. Min Range: -1.5346

Max Act: 0.8403. Min Act: -0.0000

Data Index: 440491 (C4 (Web Text))

Max Activating Token Index: 873