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

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

Neuron 4855 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.9423. Min Act: -0.0001

Data Index: 806266 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7927. Min Act: -0.0001

Data Index: 582299 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1291323 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7494. Min Act: -0.0000

Data Index: 660491 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8593. Min Act: -0.0001

Data Index: 886826 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1325708 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8399. Min Act: -0.0000

Data Index: 964953 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8601. Min Act: -0.0001

Data Index: 867186 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8678. Min Act: -0.0001

Data Index: 455024 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7742. Min Act: -0.0001

Data Index: 512050 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7844. Min Act: -0.0001

Data Index: 837137 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7876. Min Act: -0.0001

Data Index: 1190703 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8259. Min Act: -0.0000

Data Index: 515799 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7850. Min Act: -0.0000

Data Index: 212030 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7811. Min Act: -0.0000

Data Index: 815936 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8080. Min Act: -0.0000

Data Index: 431521 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1112488 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1342462 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7644. Min Act: -0.0001

Data Index: 358283 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7829. Min Act: -0.0001

Data Index: 98187 (C4 (Web Text))

Max Activating Token Index: 701