Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0437. Min Range: -2.0437

Max Act: 2.0437. Min Act: -0.0000

Data Index: 284812 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.8462. Min Act: -0.0000

Data Index: 1300993 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.8967. Min Act: -0.0000

Data Index: 295936 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1056739 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.7847. Min Act: -0.0000

Data Index: 851505 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.7627. Min Act: -0.0000

Data Index: 990997 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6356. Min Act: -0.0000

Data Index: 540827 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.7636. Min Act: -0.0000

Data Index: 914058 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6712. Min Act: -0.0000

Data Index: 817467 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6395. Min Act: -0.0000

Data Index: 278070 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.7243. Min Act: -0.0000

Data Index: 414750 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1012344 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6538. Min Act: -0.0000

Data Index: 540220 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1147947 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.5865. Min Act: -0.0000

Data Index: 340516 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1294153 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.7489. Min Act: -0.0000

Data Index: 200632 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6156. Min Act: -0.0000

Data Index: 896387 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.6451. Min Act: -0.0000

Data Index: 908569 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 2.0437. Min Range: -2.0437

Max Act: 1.5403. Min Act: -0.0000

Data Index: 986293 (C4 (Web Text))

Max Activating Token Index: 1007