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

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

Neuron 1719 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6728. Min Act: -0.0000

Data Index: 156632 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5415. Min Act: -0.0000

Data Index: 801882 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1098570 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5175. Min Act: -0.0000

Data Index: 506875 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5023. Min Act: -0.0000

Data Index: 565760 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4607. Min Act: -0.0000

Data Index: 876338 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4435. Min Act: -0.0000

Data Index: 709521 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1121953 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4750. Min Act: -0.0000

Data Index: 333893 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4562. Min Act: -0.0000

Data Index: 606796 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4518. Min Act: -0.0000

Data Index: 729755 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4439. Min Act: -0.0000

Data Index: 392071 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4699. Min Act: -0.0000

Data Index: 375082 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4492. Min Act: -0.0000

Data Index: 114925 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4434. Min Act: -0.0000

Data Index: 605296 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4261. Min Act: -0.0000

Data Index: 783632 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4268. Min Act: -0.0000

Data Index: 250387 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4099. Min Act: -0.0000

Data Index: 678239 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3982. Min Act: -0.0000

Data Index: 223994 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4096. Min Act: -0.0000

Data Index: 848364 (C4 (Web Text))

Max Activating Token Index: 393