Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 28 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7961. Min Act: -0.0001

Data Index: 1371669 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7440. Min Act: -0.0001

Data Index: 1648767 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7515. Min Act: -0.0001

Data Index: 1382173 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6897. Min Act: -0.0001

Data Index: 1616721 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7404. Min Act: -0.0001

Data Index: 1444321 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7166. Min Act: -0.0001

Data Index: 1634330 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.7061. Min Act: -0.0001

Data Index: 1436982 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6431. Min Act: -0.0001

Data Index: 1541068 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6790. Min Act: -0.0001

Data Index: 1450851 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.5730. Min Act: -0.0001

Data Index: 1560047 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6613. Min Act: -0.0001

Data Index: 1635108 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6132. Min Act: -0.0001

Data Index: 1383925 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6087. Min Act: -0.0001

Data Index: 1428614 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6519. Min Act: -0.0001

Data Index: 1651263 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6046. Min Act: -0.0001

Data Index: 1648202 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6471. Min Act: -0.0001

Data Index: 1372312 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6462. Min Act: -0.0001

Data Index: 1415100 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.6384. Min Act: -0.0001

Data Index: 1511482 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.5898. Min Act: -0.0001

Data Index: 1472626 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 1.7961. Min Range: -1.7961

Max Act: 1.5468. Min Act: -0.0001

Data Index: 1572923 (Python Code)

Max Activating Token Index: 154