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

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

Neuron 1806 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.2344. Min Act: -0.0000

Data Index: 373737 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1333355 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1180876 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0568. Min Act: -0.0000

Data Index: 225223 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0200. Min Act: -0.0000

Data Index: 3016 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0689. Min Act: -0.0000

Data Index: 876996 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0928. Min Act: -0.0000

Data Index: 701182 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1142116 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0614. Min Act: -0.0000

Data Index: 527373 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0181. Min Act: -0.0000

Data Index: 370566 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9297. Min Act: -0.0000

Data Index: 170133 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9016. Min Act: -0.0000

Data Index: 561310 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.8983. Min Act: -0.0000

Data Index: 156951 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9507. Min Act: -0.0000

Data Index: 61524 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9066. Min Act: -0.0000

Data Index: 709230 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1034045 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9238. Min Act: -0.0000

Data Index: 643180 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1305041 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9404. Min Act: -0.0000

Data Index: 584167 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9356. Min Act: -0.0000

Data Index: 927088 (C4 (Web Text))

Max Activating Token Index: 308