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

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

Neuron 2765 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: 1.3483. Min Range: -1.3483

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1351432 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1342233 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1354892 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1426398 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.8350. Min Act: -0.0000

Data Index: 27641 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.7981. Min Act: 0.0000

Data Index: 223899 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1313563 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.7175. Min Act: -0.0000

Data Index: 472578 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1234874 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6821. Min Act: -0.0000

Data Index: 78528 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1531120 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6522. Min Act: -0.0000

Data Index: 524565 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1541532 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6147. Min Act: -0.0000

Data Index: 963712 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6576. Min Act: -0.0000

Data Index: 370607 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1122009 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1651484 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1511347 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1629177 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1418852 (Python Code)

Max Activating Token Index: 479