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

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

Neuron 818 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.4998. Min Act: -0.0001

Data Index: 673431 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.2374. Min Act: -0.0002

Data Index: 1146016 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.3815. Min Act: -0.0001

Data Index: 1124333 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1463. Min Act: -0.0001

Data Index: 540010 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0458. Min Act: -0.0001

Data Index: 629327 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9456. Min Act: -0.0001

Data Index: 191011 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0747. Min Act: -0.0002

Data Index: 77428 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1334. Min Act: -0.0001

Data Index: 309351 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1124. Min Act: -0.0001

Data Index: 1128487 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1335806 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1178284 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9552. Min Act: -0.0001

Data Index: 1117162 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0609. Min Act: -0.0001

Data Index: 900384 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9476. Min Act: -0.0001

Data Index: 606366 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.0833. Min Act: -0.0001

Data Index: 921298 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9675. Min Act: -0.0001

Data Index: 132797 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9987. Min Act: -0.0001

Data Index: 969270 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.4998. Min Range: -1.4998

Max Act: 1.1096. Min Act: -0.0001

Data Index: 1226567 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9531. Min Act: -0.0001

Data Index: 409172 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.4998. Min Range: -1.4998

Max Act: 0.9552. Min Act: -0.0001

Data Index: 859699 (C4 (Web Text))

Max Activating Token Index: 408