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

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

Neuron 3116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3499. Min Act: -0.0000

Data Index: 1097146 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1294229 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2558. Min Act: -0.0000

Data Index: 1511492 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3646. Min Act: -0.0000

Data Index: 1546490 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1114706 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3365. Min Act: -0.0000

Data Index: 183983 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2547. Min Act: -0.0000

Data Index: 1041731 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.4612. Min Act: -0.0000

Data Index: 443055 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2441. Min Act: -0.0000

Data Index: 1408545 (Python Code)

Max Activating Token Index: 517

Text #9

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2380. Min Act: -0.0000

Data Index: 1514051 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1418369 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3109. Min Act: -0.0000

Data Index: 1505210 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.3023. Min Act: -0.0000

Data Index: 1654885 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.1559. Min Act: -0.0000

Data Index: 1590370 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.1555. Min Act: -0.0000

Data Index: 847393 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2468. Min Act: -0.0000

Data Index: 276813 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.2403. Min Act: -0.0000

Data Index: 1457045 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.0926. Min Act: -0.0000

Data Index: 1608643 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1566525 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 2.4612. Min Range: -2.4612

Max Act: 2.0202. Min Act: -0.0000

Data Index: 1387251 (Python Code)

Max Activating Token Index: 147