Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4633. Min Act: -0.0001

Data Index: 1307175 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4464. Min Act: -0.0001

Data Index: 222636 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4122. Min Act: -0.0001

Data Index: 692122 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3447. Min Act: -0.0001

Data Index: 76648 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1159493 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1029076 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3612. Min Act: -0.0001

Data Index: 297579 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.2630. Min Act: -0.0001

Data Index: 205855 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3304. Min Act: -0.0001

Data Index: 532907 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3402. Min Act: -0.0001

Data Index: 938710 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3265. Min Act: -0.0001

Data Index: 1072011 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3333. Min Act: -0.0001

Data Index: 957259 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3516. Min Act: -0.0001

Data Index: 912764 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3624. Min Act: -0.0001

Data Index: 644537 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3371. Min Act: -0.0001

Data Index: 858066 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3199. Min Act: -0.0001

Data Index: 271710 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1131182 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1144018 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3211. Min Act: -0.0001

Data Index: 607107 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3274. Min Act: -0.0001

Data Index: 679793 (C4 (Web Text))

Max Activating Token Index: 43