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

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

Neuron 3129 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: 0.1487. Min Range: -0.1487

Max Act: 0.1412. Min Act: -0.0001

Data Index: 786515 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1487. Min Act: -0.0001

Data Index: 499264 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1322. Min Act: -0.0001

Data Index: 864700 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1256411 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1338. Min Act: -0.0001

Data Index: 882913 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1289. Min Act: -0.0001

Data Index: 831659 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1289. Min Act: -0.0001

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1236. Min Act: -0.0001

Data Index: 74349 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1091012 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1289. Min Act: -0.0001

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1274. Min Act: -0.0001

Data Index: 32603 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1170865 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1258. Min Act: -0.0001

Data Index: 61451 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1242. Min Act: -0.0001

Data Index: 333671 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1276. Min Act: -0.0001

Data Index: 224791 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1217. Min Act: -0.0001

Data Index: 456979 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1229. Min Act: -0.0001

Data Index: 441384 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1244. Min Act: -0.0001

Data Index: 777432 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1169. Min Act: -0.0001

Data Index: 948248 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1216. Min Act: -0.0001

Data Index: 93445 (C4 (Web Text))

Max Activating Token Index: 331