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

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

Neuron 2429 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.5674. Min Act: -0.0000

Data Index: 519905 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1117796 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1332045 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.0854. Min Act: -0.0000

Data Index: 80995 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.5674. Min Range: -1.5674

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1270267 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1650672 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8794. Min Act: -0.0000

Data Index: 700933 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1472605 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1519510 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8506. Min Act: -0.0000

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1647922 (Python Code)

Max Activating Token Index: 714

Text #11

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8031. Min Act: -0.0000

Data Index: 329992 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1462063 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1264658 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1446322 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1545540 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1396946 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1100331 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1593709 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 1.5674. Min Range: -1.5674

Max Act: 0.7566. Min Act: -0.0000

Data Index: 596138 (C4 (Web Text))

Max Activating Token Index: 328