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

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

Neuron 4081 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1527. Min Act: -0.0001

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1208810 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1470. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1362. Min Act: -0.0001

Data Index: 527199 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1328. Min Act: -0.0001

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1284. Min Act: -0.0001

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1284. Min Act: -0.0001

Data Index: 573914 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1204. Min Act: -0.0000

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1230. Min Act: -0.0000

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1106158 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1173. Min Act: -0.0001

Data Index: 670174 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1202. Min Act: -0.0000

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1191. Min Act: -0.0000

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1182305 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1132. Min Act: -0.0000

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1092. Min Act: -0.0000

Data Index: 105193 (C4 (Web Text))

Max Activating Token Index: 93