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

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

Neuron 1807 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: 2.1820. Min Range: -2.1820

Max Act: 2.1344. Min Act: -0.0000

Data Index: 381508 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1076. Min Act: -0.0000

Data Index: 1345154 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1355. Min Act: -0.0000

Data Index: 283050 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1283. Min Act: -0.0000

Data Index: 1286830 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1820. Min Act: -0.0000

Data Index: 315053 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0292. Min Act: -0.0000

Data Index: 75274 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.9326. Min Act: -0.0000

Data Index: 998827 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.8622. Min Act: -0.0000

Data Index: 526710 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.9613. Min Act: -0.0000

Data Index: 14921 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7440. Min Act: -0.0000

Data Index: 905402 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7288. Min Act: -0.0001

Data Index: 36546 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.8224. Min Act: -0.0000

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7974. Min Act: -0.0000

Data Index: 458048 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7803. Min Act: -0.0000

Data Index: 70310 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7373. Min Act: -0.0000

Data Index: 457795 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7344. Min Act: -0.0000

Data Index: 64498 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1127801 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7082. Min Act: -0.0001

Data Index: 823692 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.6897. Min Act: -0.0000

Data Index: 1029155 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 2.1820. Min Range: -2.1820

Max Act: 1.7794. Min Act: -0.0000

Data Index: 906902 (C4 (Web Text))

Max Activating Token Index: 837