Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1461 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1306. Min Act: -0.0001

Data Index: 984516 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1148446 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1258. Min Act: -0.0001

Data Index: 407357 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1235. Min Act: -0.0001

Data Index: 123705 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 547970 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1261. Min Act: -0.0001

Data Index: 25915 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1301. Min Act: -0.0001

Data Index: 8691 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1251. Min Act: -0.0001

Data Index: 979968 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1032979 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1273. Min Act: -0.0001

Data Index: 471327 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1247. Min Act: -0.0001

Data Index: 407071 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1122. Min Act: -0.0001

Data Index: 226685 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1299606 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1192. Min Act: -0.0001

Data Index: 233514 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1023845 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1039. Min Act: -0.0001

Data Index: 844138 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1118. Min Act: -0.0001

Data Index: 914874 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1100. Min Act: -0.0001

Data Index: 276593 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1059. Min Act: -0.0001

Data Index: 272528 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1080. Min Act: -0.0001

Data Index: 990023 (C4 (Web Text))

Max Activating Token Index: 342