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

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

Neuron 728 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: 1.6214. Min Range: -1.6214

Max Act: 1.6214. Min Act: -0.0001

Data Index: 839633 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.4728. Min Act: -0.0001

Data Index: 495122 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.3912. Min Act: -0.0001

Data Index: 42358 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.4172. Min Act: -0.0001

Data Index: 948720 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.3721. Min Act: -0.0001

Data Index: 912966 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.2860. Min Act: -0.0001

Data Index: 754480 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.2157. Min Act: -0.0001

Data Index: 1320556 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.2944. Min Act: -0.0001

Data Index: 1312195 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1141857 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.2372. Min Act: -0.0001

Data Index: 637372 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.2216. Min Act: -0.0001

Data Index: 525599 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1828. Min Act: -0.0001

Data Index: 51466 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1335. Min Act: -0.0001

Data Index: 438745 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1462. Min Act: -0.0001

Data Index: 957999 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1068. Min Act: -0.0001

Data Index: 209227 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1644. Min Act: -0.0001

Data Index: 964947 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.1180. Min Act: -0.0001

Data Index: 113233 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.0790. Min Act: -0.0001

Data Index: 458707 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.0467. Min Act: -0.0001

Data Index: 680342 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 1.6214. Min Range: -1.6214

Max Act: 1.0218. Min Act: -0.0001

Data Index: 225320 (C4 (Web Text))

Max Activating Token Index: 182