Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2620 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0000

Data Index: 774068 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1131235 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1441. Min Act: -0.0000

Data Index: 141784 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1272. Min Act: -0.0000

Data Index: 629877 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1231282 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1269. Min Act: -0.0000

Data Index: 187156 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1127. Min Act: -0.0000

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1137. Min Act: -0.0000

Data Index: 429617 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1130922 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1315169 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1189. Min Act: -0.0000

Data Index: 638944 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1112. Min Act: -0.0000

Data Index: 61481 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1138. Min Act: -0.0000

Data Index: 247241 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1136. Min Act: -0.0000

Data Index: 366918 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1148. Min Act: -0.0000

Data Index: 189396 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1113. Min Act: -0.0000

Data Index: 213147 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1334154 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1060. Min Act: -0.0000

Data Index: 80322 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1024232 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1075. Min Act: -0.0000

Data Index: 57647 (C4 (Web Text))

Max Activating Token Index: 554