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

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

Neuron 2854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.6956. Min Act: -0.0000

Data Index: 418822 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.7532. Min Act: -0.0000

Data Index: 144168 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1059621 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.4877. Min Act: -0.0000

Data Index: 641591 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.3109. Min Act: -0.0000

Data Index: 238884 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1101515 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.2387. Min Act: -0.0000

Data Index: 186910 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0932. Min Act: -0.0000

Data Index: 742866 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.2151. Min Act: -0.0000

Data Index: 337391 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.1771. Min Act: -0.0000

Data Index: 729148 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.1281. Min Act: -0.0000

Data Index: 397881 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1347178 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.1462. Min Act: -0.0000

Data Index: 637147 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1161265 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0854. Min Act: -0.0000

Data Index: 810294 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0638. Min Act: 0.0000

Data Index: 1348174 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0316. Min Act: 0.0000

Data Index: 499669 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0654. Min Act: -0.0000

Data Index: 736440 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0507. Min Act: -0.0000

Data Index: 654167 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.7532. Min Range: -1.7532

Max Act: 1.0421. Min Act: -0.0000

Data Index: 84923 (C4 (Web Text))

Max Activating Token Index: 910