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

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

Neuron 4893 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0001

Data Index: 681437 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2556. Min Act: -0.0001

Data Index: 1278954 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1031453 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2506. Min Act: -0.0001

Data Index: 1168569 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2334. Min Act: -0.0001

Data Index: 605353 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2044. Min Act: -0.0001

Data Index: 1327519 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2358. Min Act: -0.0001

Data Index: 718573 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1957. Min Act: -0.0001

Data Index: 967816 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2181. Min Act: -0.0001

Data Index: 856955 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2132. Min Act: -0.0001

Data Index: 995278 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2131. Min Act: -0.0001

Data Index: 575649 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2205. Min Act: -0.0001

Data Index: 611270 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2201. Min Act: -0.0001

Data Index: 581937 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1129052 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1071757 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1306288 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2086. Min Act: -0.0001

Data Index: 249540 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1329422 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2160. Min Act: -0.0001

Data Index: 67862 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2172. Min Act: -0.0001

Data Index: 949844 (C4 (Web Text))

Max Activating Token Index: 839