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

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

Neuron 1433 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: 0.3473. Min Range: -0.3473

Max Act: 0.3428. Min Act: -0.0000

Data Index: 431269 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3420. Min Act: -0.0001

Data Index: 692718 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3343. Min Act: -0.0001

Data Index: 537976 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1027745 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3291. Min Act: -0.0000

Data Index: 595067 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3473. Min Act: -0.0000

Data Index: 56098 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3193. Min Act: -0.0001

Data Index: 195088 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3248. Min Act: -0.0000

Data Index: 107155 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3158. Min Act: -0.0000

Data Index: 13142 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3048. Min Act: -0.0000

Data Index: 901501 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2920. Min Act: -0.0000

Data Index: 885635 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2900. Min Act: -0.0000

Data Index: 349188 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2878. Min Act: -0.0001

Data Index: 296040 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2743. Min Act: -0.0000

Data Index: 267611 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2647. Min Act: -0.0000

Data Index: 161379 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1178151 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1079916 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2501. Min Act: -0.0000

Data Index: 975446 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1292086 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2693. Min Act: -0.0000

Data Index: 584030 (C4 (Web Text))

Max Activating Token Index: 693