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

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

Neuron 2536 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.2385. Min Act: -0.0000

Data Index: 212781 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.8003. Min Act: -0.0000

Data Index: 119697 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.3747. Min Act: -0.0000

Data Index: 799293 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.4868. Min Act: -0.0000

Data Index: 1185008 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.4563. Min Act: -0.0000

Data Index: 1001175 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.4371. Min Act: -0.0000

Data Index: 132757 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.3785. Min Act: -0.0000

Data Index: 284764 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.2981. Min Act: -0.0000

Data Index: 586846 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.1632. Min Act: -0.0000

Data Index: 308837 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.3164. Min Act: -0.0000

Data Index: 1226760 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.9741. Min Act: -0.0000

Data Index: 875368 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.0945. Min Act: -0.0000

Data Index: 1115797 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.0959. Min Act: -0.0000

Data Index: 15208 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.8917. Min Act: -0.0000

Data Index: 737892 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 4.2385. Min Range: -4.2385

Max Act: 3.2033. Min Act: -0.0000

Data Index: 673855 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.8205. Min Act: -0.0000

Data Index: 44156 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.9472. Min Act: -0.0000

Data Index: 66632 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.9400. Min Act: -0.0000

Data Index: 339797 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.9147. Min Act: -0.0000

Data Index: 543020 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 4.2385. Min Range: -4.2385

Max Act: 2.9044. Min Act: -0.0000

Data Index: 1032490 (C4 (Web Text))

Max Activating Token Index: 481