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

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

Neuron 4221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.5223. Min Act: -0.0000

Data Index: 1011704 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.5549. Min Act: -0.0000

Data Index: 327433 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.4404. Min Act: -0.0000

Data Index: 894904 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2376. Min Act: -0.0000

Data Index: 279340 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.4294. Min Act: -0.0000

Data Index: 712858 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2818. Min Act: -0.0000

Data Index: 402178 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.2176. Min Act: -0.0000

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1906. Min Act: -0.0000

Data Index: 43886 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1493. Min Act: -0.0000

Data Index: 859978 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.0389. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.9245. Min Act: -0.0000

Data Index: 783640 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.1306. Min Act: -0.0000

Data Index: 503451 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.9441. Min Act: -0.0000

Data Index: 623349 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 2.5549. Min Range: -2.5549

Max Act: 2.0805. Min Act: -0.0000

Data Index: 920027 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.8863. Min Act: -0.0000

Data Index: 338896 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.8860. Min Act: -0.0000

Data Index: 113230 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.8762. Min Act: -0.0000

Data Index: 779473 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.9743. Min Act: -0.0000

Data Index: 776059 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.8228. Min Act: -0.0000

Data Index: 963737 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 2.5549. Min Range: -2.5549

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1091156 (C4 (Web Text))

Max Activating Token Index: 929