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

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

Neuron 550 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5731. Min Act: -0.0000

Data Index: 253254 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5465. Min Act: -0.0001

Data Index: 1165398 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5354. Min Act: -0.0000

Data Index: 421705 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5257. Min Act: -0.0001

Data Index: 9498 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5138. Min Act: -0.0000

Data Index: 28883 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4827. Min Act: -0.0001

Data Index: 714757 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5334. Min Act: -0.0001

Data Index: 16261 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.5078. Min Act: 0.0000

Data Index: 1137276 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4920. Min Act: -0.0001

Data Index: 1180248 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4952. Min Act: -0.0000

Data Index: 711031 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4622. Min Act: -0.0001

Data Index: 669175 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4542. Min Act: -0.0001

Data Index: 897045 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4868. Min Act: -0.0000

Data Index: 563032 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4824. Min Act: -0.0001

Data Index: 141087 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4504. Min Act: -0.0001

Data Index: 1065110 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4355. Min Act: -0.0001

Data Index: 674142 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4305. Min Act: -0.0000

Data Index: 14830 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4400. Min Act: 0.0000

Data Index: 239351 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4414. Min Act: -0.0001

Data Index: 1233865 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.5731. Min Range: -0.5731

Max Act: 0.4255. Min Act: -0.0000

Data Index: 900976 (C4 (Web Text))

Max Activating Token Index: 919