Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0001

Data Index: 103738 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6661. Min Act: -0.0001

Data Index: 208715 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6214. Min Act: -0.0001

Data Index: 935787 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1051547 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5865. Min Act: -0.0001

Data Index: 1043970 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5625. Min Act: -0.0001

Data Index: 377615 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5624. Min Act: -0.0001

Data Index: 692032 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5876. Min Act: -0.0001

Data Index: 1353737 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1123450 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5350. Min Act: -0.0001

Data Index: 490661 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5387. Min Act: -0.0001

Data Index: 326042 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5526. Min Act: -0.0001

Data Index: 172508 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1169047 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5258. Min Act: -0.0001

Data Index: 544427 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5445. Min Act: -0.0001

Data Index: 176018 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5235. Min Act: -0.0001

Data Index: 1108795 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5299. Min Act: -0.0001

Data Index: 1219878 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5239. Min Act: -0.0001

Data Index: 1007603 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5279. Min Act: -0.0001

Data Index: 1212509 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5065. Min Act: -0.0001

Data Index: 706358 (C4 (Web Text))

Max Activating Token Index: 1002