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

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

Neuron 836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4143. Min Range: -2.4143

Max Act: 2.4143. Min Act: -0.0000

Data Index: 771350 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.9624. Min Act: -0.0000

Data Index: 914554 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.6419. Min Act: -0.0000

Data Index: 158245 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1170679 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.8246. Min Act: -0.0000

Data Index: 473922 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.7253. Min Act: -0.0000

Data Index: 507683 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1049855 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.7893. Min Act: -0.0000

Data Index: 544941 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1322895 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1205008 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.6173. Min Act: -0.0000

Data Index: 1022074 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.4283. Min Act: -0.0000

Data Index: 328280 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1218465 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.5631. Min Act: -0.0000

Data Index: 135986 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1300031 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.3494. Min Act: -0.0000

Data Index: 79761 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.6431. Min Act: -0.0000

Data Index: 473536 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1134362 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1301510 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.4143. Min Range: -2.4143

Max Act: 1.4728. Min Act: -0.0000

Data Index: 508513 (C4 (Web Text))

Max Activating Token Index: 893