Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2207 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0002

Data Index: 909735 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1463. Min Act: -0.0002

Data Index: 392979 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1174622 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1367. Min Act: -0.0002

Data Index: 336574 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1360. Min Act: -0.0002

Data Index: 919374 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1183. Min Act: -0.0002

Data Index: 773993 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1147779 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1188. Min Act: -0.0002

Data Index: 275360 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1337752 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1161307 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1237. Min Act: -0.0002

Data Index: 805431 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1183. Min Act: -0.0002

Data Index: 664683 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1161. Min Act: -0.0002

Data Index: 544656 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1130528 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1053601 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1108. Min Act: -0.0002

Data Index: 895502 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1078325 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1189598 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1148. Min Act: -0.0002

Data Index: 361759 (C4 (Web Text))

Max Activating Token Index: 947