Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1428. Min Range: -2.1428

Max Act: 2.1428. Min Act: -0.0000

Data Index: 991188 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 2.1428. Min Range: -2.1428

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1084244 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.8331. Min Act: -0.0001

Data Index: 623403 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1105392 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.8196. Min Act: -0.0001

Data Index: 949176 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7734. Min Act: -0.0001

Data Index: 302295 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7134. Min Act: -0.0001

Data Index: 689263 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6979. Min Act: -0.0000

Data Index: 370069 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7136. Min Act: -0.0000

Data Index: 63841 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7599. Min Act: -0.0000

Data Index: 252704 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6514. Min Act: -0.0000

Data Index: 904940 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6441. Min Act: -0.0000

Data Index: 176302 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.7396. Min Act: -0.0000

Data Index: 273421 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6493. Min Act: -0.0000

Data Index: 1168229 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6255. Min Act: -0.0001

Data Index: 972348 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.6130. Min Act: 0.0000

Data Index: 926798 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.5939. Min Act: -0.0001

Data Index: 1160891 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.5185. Min Act: -0.0000

Data Index: 530759 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.5922. Min Act: -0.0000

Data Index: 707721 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 2.1428. Min Range: -2.1428

Max Act: 1.5006. Min Act: -0.0001

Data Index: 774766 (C4 (Web Text))

Max Activating Token Index: 47