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

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

Neuron 4032 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4912. Min Act: -0.0001

Data Index: 271643 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4593. Min Act: -0.0002

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4515. Min Act: -0.0002

Data Index: 286288 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4312. Min Act: -0.0002

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4637. Min Act: -0.0002

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4257. Min Act: -0.0002

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4320. Min Act: -0.0002

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4173. Min Act: -0.0001

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4117. Min Act: -0.0002

Data Index: 58827 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4035. Min Act: -0.0001

Data Index: 36450 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3833. Min Act: -0.0002

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4338. Min Act: -0.0002

Data Index: 1280979 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4055. Min Act: -0.0002

Data Index: 759035 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3968. Min Act: -0.0002

Data Index: 984876 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4058. Min Act: -0.0001

Data Index: 588563 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3824. Min Act: -0.0002

Data Index: 602428 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4220. Min Act: -0.0002

Data Index: 460727 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3930. Min Act: -0.0002

Data Index: 784090 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3642. Min Act: -0.0002

Data Index: 286237 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4131. Min Act: -0.0002

Data Index: 775522 (C4 (Web Text))

Max Activating Token Index: 982