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

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

Neuron 3448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1008680 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1183. Min Act: -0.0001

Data Index: 796478 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1212. Min Act: -0.0001

Data Index: 505741 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1242. Min Act: -0.0001

Data Index: 334818 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1141. Min Act: -0.0001

Data Index: 159741 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1099. Min Act: -0.0001

Data Index: 429089 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1064531 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1311424 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1291664 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1000734 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1156. Min Act: -0.0001

Data Index: 108917 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1124. Min Act: -0.0001

Data Index: 110487 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1013729 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1111. Min Act: -0.0000

Data Index: 331020 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1154. Min Act: -0.0001

Data Index: 222444 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1129372 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1146. Min Act: -0.0001

Data Index: 530287 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1157179 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1143. Min Act: -0.0001

Data Index: 216514 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1242. Min Range: -0.1242

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1256377 (C4 (Web Text))

Max Activating Token Index: 492