Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1352 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1243. Min Act: -0.0001

Data Index: 69431 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1272. Min Act: -0.0001

Data Index: 966171 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1265. Min Act: -0.0001

Data Index: 393192 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1281791 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1234. Min Act: -0.0001

Data Index: 468335 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1233115 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1173. Min Act: -0.0001

Data Index: 83103 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1257. Min Act: -0.0001

Data Index: 691913 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1256486 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1204. Min Act: -0.0001

Data Index: 337029 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1202. Min Act: -0.0001

Data Index: 659292 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1192. Min Act: -0.0001

Data Index: 969544 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1198. Min Act: -0.0001

Data Index: 173214 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1153. Min Act: -0.0001

Data Index: 303208 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1234. Min Act: -0.0001

Data Index: 121386 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1312028 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1134. Min Act: -0.0001

Data Index: 682462 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1140. Min Act: -0.0001

Data Index: 153978 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1308538 (C4 (Web Text))

Max Activating Token Index: 598