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

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

Neuron 5918 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2409. Min Range: -2.2409

Max Act: 2.2409. Min Act: -0.0000

Data Index: 321824 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.8635. Min Act: -0.0000

Data Index: 628607 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1325937 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.7362. Min Act: -0.0000

Data Index: 3082 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.6804. Min Act: -0.0000

Data Index: 478643 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1242843 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.6045. Min Act: -0.0000

Data Index: 688100 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.5629. Min Act: -0.0000

Data Index: 823706 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.3872. Min Act: -0.0000

Data Index: 1204908 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2688. Min Act: -0.0000

Data Index: 61042 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2398. Min Act: -0.0000

Data Index: 590862 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2421. Min Act: -0.0000

Data Index: 3692 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1124071 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2042. Min Act: -0.0000

Data Index: 478135 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.1954. Min Act: -0.0000

Data Index: 152905 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1163142 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1083979 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.1481. Min Act: -0.0000

Data Index: 573684 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.1139. Min Act: -0.0000

Data Index: 15662 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.2409. Min Range: -2.2409

Max Act: 1.1281. Min Act: -0.0000

Data Index: 925628 (C4 (Web Text))

Max Activating Token Index: 415