Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 729 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.7941. Min Act: -0.0000

Data Index: 272462 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.7086. Min Act: -0.0000

Data Index: 220862 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.4104. Min Act: -0.0000

Data Index: 777465 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.3912. Min Act: -0.0000

Data Index: 35429 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.3654. Min Act: -0.0000

Data Index: 1239375 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.3159. Min Act: -0.0000

Data Index: 333905 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.2952. Min Act: -0.0000

Data Index: 13335 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.4094. Min Act: -0.0000

Data Index: 185358 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.6243. Min Act: -0.0000

Data Index: 939695 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.2342. Min Act: -0.0000

Data Index: 835119 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.0750. Min Act: -0.0000

Data Index: 839682 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.1150. Min Act: -0.0000

Data Index: 75106 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.2075. Min Act: -0.0000

Data Index: 999560 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.1932. Min Act: -0.0000

Data Index: 1177134 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.0716. Min Act: -0.0000

Data Index: 820535 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.1797. Min Act: -0.0000

Data Index: 829673 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.0566. Min Act: -0.0000

Data Index: 137618 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.0469. Min Act: -0.0000

Data Index: 544709 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.1431. Min Act: -0.0000

Data Index: 58931 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 2.7941. Min Range: -2.7941

Max Act: 2.1397. Min Act: -0.0000

Data Index: 262838 (C4 (Web Text))

Max Activating Token Index: 619