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

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

Neuron 3632 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: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0001

Data Index: 796387 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1803. Min Act: -0.0001

Data Index: 940584 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1644. Min Act: -0.0001

Data Index: 993304 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1504. Min Act: -0.0001

Data Index: 576160 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1404. Min Act: -0.0001

Data Index: 816108 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1467. Min Act: -0.0001

Data Index: 621528 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1051833 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1275. Min Act: -0.0001

Data Index: 145800 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1257. Min Act: -0.0001

Data Index: 965607 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1275. Min Act: -0.0001

Data Index: 557413 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1244. Min Act: -0.0001

Data Index: 636414 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1305144 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1241. Min Act: -0.0001

Data Index: 180122 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1212. Min Act: -0.0001

Data Index: 571664 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1178. Min Act: -0.0001

Data Index: 708902 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1132298 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1166. Min Act: -0.0001

Data Index: 900980 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1196. Min Act: -0.0001

Data Index: 459118 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1140. Min Act: -0.0001

Data Index: 998322 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1315726 (C4 (Web Text))

Max Activating Token Index: 898