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

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

Neuron 560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.7474. Min Act: -0.0000

Data Index: 950137 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.3625. Min Act: -0.0000

Data Index: 48 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.2626. Min Act: -0.0000

Data Index: 454387 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.2118. Min Act: -0.0000

Data Index: 1245621 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.1927. Min Act: -0.0000

Data Index: 283253 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.1091. Min Act: -0.0000

Data Index: 298309 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.1643. Min Act: -0.0000

Data Index: 796541 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.1074. Min Act: -0.0000

Data Index: 746356 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.1402. Min Act: -0.0000

Data Index: 768343 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1251329 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9496. Min Act: -0.0000

Data Index: 384338 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.7474. Min Range: -1.7474

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1295200 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1016873 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1263080 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1133478 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9515. Min Act: -0.0000

Data Index: 375031 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1322481 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1174176 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.8965. Min Act: -0.0000

Data Index: 389727 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.7474. Min Range: -1.7474

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1199879 (C4 (Web Text))

Max Activating Token Index: 990