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

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

Neuron 3603 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.8640. Min Act: -0.0000

Data Index: 793089 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.8430. Min Act: -0.0000

Data Index: 22585 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.7111. Min Act: -0.0000

Data Index: 772915 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.5270. Min Act: -0.0000

Data Index: 879902 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.4512. Min Act: -0.0000

Data Index: 965494 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.4363. Min Act: -0.0000

Data Index: 1230903 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.9585. Min Act: -0.0000

Data Index: 175078 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.8640. Min Range: -2.8640

Max Act: 2.0225. Min Act: -0.0000

Data Index: 82774 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.9282. Min Act: -0.0000

Data Index: 1018007 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.9184. Min Act: -0.0000

Data Index: 415250 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1000114 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.7538. Min Act: -0.0000

Data Index: 365526 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.9435. Min Act: -0.0000

Data Index: 385323 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1284398 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.6432. Min Act: -0.0000

Data Index: 403226 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1263455 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1209233 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.6464. Min Act: -0.0000

Data Index: 95430 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.6801. Min Act: -0.0000

Data Index: 441556 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 2.8640. Min Range: -2.8640

Max Act: 1.5726. Min Act: -0.0000

Data Index: 1269849 (C4 (Web Text))

Max Activating Token Index: 785