Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 931 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1435. Min Act: -0.0003

Data Index: 1165370 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1406. Min Act: -0.0003

Data Index: 780897 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1330. Min Act: -0.0004

Data Index: 751599 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1337. Min Act: -0.0003

Data Index: 976323 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1267. Min Act: -0.0003

Data Index: 22385 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1268. Min Act: -0.0003

Data Index: 334881 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1312. Min Act: -0.0003

Data Index: 703834 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1208. Min Act: -0.0003

Data Index: 940231 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1194. Min Act: -0.0003

Data Index: 1086066 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1183. Min Act: -0.0004

Data Index: 409181 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1211. Min Act: -0.0003

Data Index: 1165426 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1183. Min Act: -0.0003

Data Index: 418454 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1254. Min Act: -0.0004

Data Index: 345225 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1197. Min Act: -0.0003

Data Index: 334049 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1186. Min Act: -0.0003

Data Index: 770103 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1229. Min Act: -0.0003

Data Index: 547292 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1162. Min Act: -0.0004

Data Index: 850777 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1211. Min Act: -0.0003

Data Index: 577886 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1177. Min Act: -0.0003

Data Index: 710971 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1148. Min Act: -0.0004

Data Index: 1284755 (C4 (Web Text))

Max Activating Token Index: 138