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

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

Neuron 1496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2758. Min Act: -0.0001

Data Index: 65345 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0001

Data Index: 885251 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2480. Min Act: -0.0001

Data Index: 154251 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1015082 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2526. Min Act: -0.0001

Data Index: 147081 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2514. Min Act: -0.0001

Data Index: 53304 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2309. Min Act: -0.0001

Data Index: 1443081 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2290. Min Act: -0.0001

Data Index: 953581 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2244. Min Act: -0.0001

Data Index: 255404 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1204211 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1631924 (Python Code)

Max Activating Token Index: 863

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2228. Min Act: -0.0001

Data Index: 440973 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2464. Min Act: -0.0001

Data Index: 173674 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2129. Min Act: -0.0001

Data Index: 792402 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2121. Min Act: -0.0001

Data Index: 627055 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1635462 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1097117 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1171109 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2177. Min Act: -0.0001

Data Index: 680852 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2149. Min Act: -0.0001

Data Index: 988089 (C4 (Web Text))

Max Activating Token Index: 391