Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.8707. Min Act: -0.0000

Data Index: 1487416 (Python Code)

Max Activating Token Index: 979

Text #1

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7131. Min Act: -0.0000

Data Index: 1407969 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1579571 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.5770. Min Act: 0.0000

Data Index: 1523830 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.5125. Min Act: -0.0000

Data Index: 1533966 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1453399 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.4166. Min Act: 0.0000

Data Index: 1549702 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1534718 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.4053. Min Act: 0.0000

Data Index: 1471051 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3527. Min Act: -0.0000

Data Index: 1528548 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.4290. Min Act: 0.0000

Data Index: 1382987 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3281. Min Act: 0.0000

Data Index: 1577495 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1582687 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3904. Min Act: 0.0000

Data Index: 1436462 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1452927 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1605749 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1604735 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1561084 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.2661. Min Act: 0.0000

Data Index: 1409881 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1402863 (Python Code)

Max Activating Token Index: 307