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

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

Neuron 406 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: 0.1310. Min Range: -0.1310

Max Act: 0.0295. Min Act: -0.0000

Data Index: 763414 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 966177 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1309. Min Act: -0.0001

Data Index: 534311 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1272. Min Act: -0.0001

Data Index: 199105 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1175. Min Act: -0.0000

Data Index: 870450 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1282. Min Act: -0.0001

Data Index: 438069 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1334477 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1239. Min Act: -0.0001

Data Index: 563274 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1220. Min Act: -0.0001

Data Index: 47397 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1202. Min Act: -0.0001

Data Index: 623876 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1189. Min Act: -0.0001

Data Index: 710861 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0465. Min Act: -0.0001

Data Index: 136954 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1075. Min Act: -0.0001

Data Index: 552355 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1154. Min Act: -0.0001

Data Index: 181023 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1275466 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1291886 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1111. Min Act: -0.0001

Data Index: 16593 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1336996 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1056. Min Act: -0.0001

Data Index: 156451 (C4 (Web Text))

Max Activating Token Index: 617