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

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

Neuron 2198 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: 0.1888. Min Range: -0.1888

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1300853 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 78545 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1493. Min Act: -0.0001

Data Index: 164421 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1406. Min Act: -0.0001

Data Index: 817316 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1396. Min Act: -0.0001

Data Index: 812541 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1284. Min Act: -0.0001

Data Index: 48254 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1276. Min Act: -0.0001

Data Index: 168028 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1232. Min Act: -0.0001

Data Index: 44100 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1200. Min Act: -0.0001

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1211944 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1279. Min Act: -0.0001

Data Index: 870799 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1141789 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1319. Min Act: -0.0001

Data Index: 519111 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1553. Min Act: -0.0001

Data Index: 813728 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1253. Min Act: -0.0001

Data Index: 950431 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1187. Min Act: -0.0001

Data Index: 461655 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1116. Min Act: -0.0001

Data Index: 218671 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1188. Min Act: -0.0001

Data Index: 839109 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1058. Min Act: -0.0001

Data Index: 170571 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1286076 (C4 (Web Text))

Max Activating Token Index: 968