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

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

Neuron 2982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6854. Min Act: -0.0001

Data Index: 1391433 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5116. Min Act: -0.0001

Data Index: 1446458 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5673. Min Act: -0.0001

Data Index: 1556873 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2778. Min Act: -0.0001

Data Index: 1575857 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2648. Min Act: -0.0001

Data Index: 1385634 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2356. Min Act: -0.0001

Data Index: 1490808 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2621. Min Act: -0.0001

Data Index: 1531350 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2658. Min Act: -0.0001

Data Index: 1642244 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2266. Min Act: -0.0001

Data Index: 1466283 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2001. Min Act: -0.0001

Data Index: 1567967 (Python Code)

Max Activating Token Index: 493

Text #10

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2990. Min Act: -0.0001

Data Index: 1447149 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1169. Min Act: -0.0001

Data Index: 1634957 (Python Code)

Max Activating Token Index: 526

Text #12

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1825. Min Act: -0.0001

Data Index: 1649861 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1519. Min Act: -0.0001

Data Index: 1476125 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1451. Min Act: -0.0001

Data Index: 1482097 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 1.6854. Min Range: -1.6854

Max Act: 0.9732. Min Act: -0.0001

Data Index: 1652125 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.0936. Min Act: -0.0001

Data Index: 1407721 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.0798. Min Act: -0.0001

Data Index: 1453381 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1048. Min Act: -0.0001

Data Index: 1499643 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.0562. Min Act: -0.0001

Data Index: 1594681 (Python Code)

Max Activating Token Index: 640