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

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

Neuron 2099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1443370 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.4054. Min Act: -0.0001

Data Index: 1627177 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3733. Min Act: -0.0001

Data Index: 1404795 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1456413 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1398440 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3194. Min Act: -0.0001

Data Index: 998619 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1601969 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1505924 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3164. Min Act: -0.0001

Data Index: 1620359 (Python Code)

Max Activating Token Index: 69

Text #9

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1618607 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1599228 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1579054 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1442615 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1450937 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1620418 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2825. Min Act: -0.0001

Data Index: 1397478 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1407554 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1424602 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1168432 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1443717 (Python Code)

Max Activating Token Index: 293