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

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

Neuron 2011 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: 0.3886. Min Range: -0.3886

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1260698 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3159. Min Act: -0.0001

Data Index: 584227 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2706. Min Act: -0.0001

Data Index: 886190 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2695. Min Act: -0.0001

Data Index: 617546 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2745. Min Act: -0.0001

Data Index: 610020 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2730. Min Act: -0.0001

Data Index: 110293 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2805. Min Act: -0.0001

Data Index: 882013 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2612. Min Act: -0.0001

Data Index: 719192 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2617. Min Act: -0.0001

Data Index: 61210 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2596. Min Act: -0.0001

Data Index: 896848 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1059945 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2395. Min Act: -0.0001

Data Index: 943665 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2667. Min Act: -0.0001

Data Index: 355685 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1355853 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1099642 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2360. Min Act: -0.0001

Data Index: 635861 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1292658 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2479. Min Act: -0.0001

Data Index: 98188 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2328. Min Act: -0.0001

Data Index: 218537 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2398. Min Act: -0.0001

Data Index: 94786 (C4 (Web Text))

Max Activating Token Index: 675