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

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

Neuron 4944 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.7477. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.5984. Min Act: -0.0000

Data Index: 852282 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6834. Min Act: -0.0000

Data Index: 1051943 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.5444. Min Act: -0.0000

Data Index: 686524 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.5888. Min Act: -0.0000

Data Index: 720617 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6961. Min Act: -0.0000

Data Index: 164668 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.5232. Min Act: -0.0000

Data Index: 94886 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.3050. Min Act: -0.0000

Data Index: 809866 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.4934. Min Act: -0.0000

Data Index: 253302 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.5220. Min Act: -0.0000

Data Index: 310102 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.3701. Min Act: -0.0000

Data Index: 560716 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.3376. Min Act: -0.0000

Data Index: 681205 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.2821. Min Act: -0.0000

Data Index: 980296 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.3195. Min Act: -0.0000

Data Index: 152429 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.4762. Min Act: -0.0000

Data Index: 1007640 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.4846. Min Act: -0.0000

Data Index: 1224630 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.3280. Min Act: -0.0000

Data Index: 195842 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.2139. Min Act: -0.0000

Data Index: 612251 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.1929. Min Act: -0.0000

Data Index: 845165 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.2877. Min Act: -0.0000

Data Index: 991101 (C4 (Web Text))

Max Activating Token Index: 958