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

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

Neuron 589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3016. Min Act: -0.0001

Data Index: 868182 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3123. Min Act: -0.0001

Data Index: 176662 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2705. Min Act: -0.0001

Data Index: 819062 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2971. Min Act: -0.0001

Data Index: 387493 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1246568 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2727. Min Act: -0.0001

Data Index: 968623 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2520. Min Act: -0.0001

Data Index: 885940 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2664. Min Act: -0.0001

Data Index: 861392 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2660. Min Act: -0.0001

Data Index: 595950 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2460. Min Act: -0.0001

Data Index: 616457 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2346. Min Act: -0.0001

Data Index: 231250 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2288. Min Act: -0.0001

Data Index: 688189 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2383. Min Act: -0.0001

Data Index: 277239 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2308. Min Act: -0.0001

Data Index: 609773 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2264. Min Act: -0.0001

Data Index: 678537 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2390. Min Act: -0.0001

Data Index: 360988 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2261. Min Act: -0.0001

Data Index: 662275 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1221994 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2311. Min Act: -0.0001

Data Index: 208381 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2127. Min Act: -0.0001

Data Index: 519047 (C4 (Web Text))

Max Activating Token Index: 316