Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.6436. Min Range: -2.6436

Max Act: 2.6436. Min Act: -0.0000

Data Index: 1186601 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.8844. Min Act: -0.0000

Data Index: 43318 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.8306. Min Act: -0.0000

Data Index: 492872 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.7926. Min Act: -0.0000

Data Index: 165088 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1182726 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.5253. Min Act: -0.0000

Data Index: 919666 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.5442. Min Act: -0.0000

Data Index: 320955 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.5167. Min Act: -0.0000

Data Index: 573585 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.4583. Min Act: -0.0000

Data Index: 90394 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.4672. Min Act: -0.0000

Data Index: 11418 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.4655. Min Act: -0.0000

Data Index: 232555 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.5401. Min Act: -0.0000

Data Index: 899190 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.3856. Min Act: -0.0000

Data Index: 1107101 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.3647. Min Act: -0.0001

Data Index: 153260 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.2914. Min Act: -0.0000

Data Index: 903744 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.4260. Min Act: -0.0001

Data Index: 934046 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1178340 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.2426. Min Act: -0.0001

Data Index: 639284 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1134895 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 2.6436. Min Range: -2.6436

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1220361 (C4 (Web Text))

Max Activating Token Index: 490