Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3368 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.3473. Min Act: -0.0001

Data Index: 237242 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1745. Min Act: -0.0001

Data Index: 324718 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.1474. Min Act: -0.0001

Data Index: 443508 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0084. Min Act: -0.0001

Data Index: 376162 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9737. Min Act: -0.0001

Data Index: 901420 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0824. Min Act: -0.0001

Data Index: 270700 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.3473. Min Range: -1.3473

Max Act: 1.0119. Min Act: -0.0001

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1220972 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9431. Min Act: -0.0001

Data Index: 383491 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.7761. Min Act: -0.0001

Data Index: 339788 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9551. Min Act: -0.0001

Data Index: 746449 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8624. Min Act: -0.0001

Data Index: 117222 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9087. Min Act: -0.0001

Data Index: 897102 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.9132. Min Act: -0.0001

Data Index: 639952 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8542. Min Act: -0.0001

Data Index: 1309862 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8530. Min Act: -0.0001

Data Index: 1085766 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1283947 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8621. Min Act: -0.0001

Data Index: 382972 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8265. Min Act: -0.0001

Data Index: 938107 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.3473. Min Range: -1.3473

Max Act: 0.8085. Min Act: -0.0001

Data Index: 489536 (C4 (Web Text))

Max Activating Token Index: 218