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

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

Neuron 1338 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0001

Data Index: 657085 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1010694 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1348. Min Act: -0.0001

Data Index: 697651 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1377. Min Act: -0.0001

Data Index: 921016 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1269. Min Act: -0.0001

Data Index: 440041 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1339685 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1146080 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1213. Min Act: -0.0001

Data Index: 226182 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1208. Min Act: -0.0001

Data Index: 737229 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1259. Min Act: -0.0001

Data Index: 1188441 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1243. Min Act: -0.0001

Data Index: 561549 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1292016 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1236. Min Act: -0.0001

Data Index: 506964 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1228. Min Act: -0.0000

Data Index: 909753 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1224. Min Act: -0.0001

Data Index: 148716 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1036687 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1190. Min Act: -0.0001

Data Index: 233890 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1034807 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1166. Min Act: -0.0001

Data Index: 427444 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1120. Min Act: -0.0001

Data Index: 489911 (C4 (Web Text))

Max Activating Token Index: 322