Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1437 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0005

Data Index: 317826 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0219. Min Act: -0.0004

Data Index: 897442 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0217. Min Act: -0.0004

Data Index: 934878 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0214. Min Act: -0.0005

Data Index: 788316 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0004

Data Index: 472875 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0206. Min Act: -0.0005

Data Index: 860143 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1493471 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0201. Min Act: -0.0005

Data Index: 976281 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0200. Min Act: -0.0005

Data Index: 304115 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0005

Data Index: 662327 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0005

Data Index: 950628 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1080913 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0200. Min Act: -0.0004

Data Index: 683922 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0194. Min Act: -0.0004

Data Index: 1462671 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1385590 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1051229 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1139956 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1385361 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1161001 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1612463 (Python Code)

Max Activating Token Index: 572