Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1065 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6940. Min Act: -0.0002

Data Index: 748329 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6346. Min Act: -0.0002

Data Index: 485232 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6471. Min Act: -0.0002

Data Index: 525694 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5964. Min Act: -0.0002

Data Index: 921588 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5853. Min Act: -0.0002

Data Index: 129306 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5782. Min Act: -0.0002

Data Index: 875126 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5461. Min Act: -0.0002

Data Index: 805811 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5432. Min Act: -0.0002

Data Index: 979576 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5428. Min Act: -0.0002

Data Index: 556683 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5381. Min Act: -0.0002

Data Index: 1212304 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5250. Min Act: -0.0002

Data Index: 232079 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5186. Min Act: -0.0002

Data Index: 346005 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5165. Min Act: -0.0002

Data Index: 323538 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5124. Min Act: -0.0002

Data Index: 1109698 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4906. Min Act: -0.0002

Data Index: 797336 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4906. Min Act: -0.0002

Data Index: 1246166 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4735. Min Act: -0.0002

Data Index: 825980 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4647. Min Act: -0.0002

Data Index: 608701 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4611. Min Act: -0.0002

Data Index: 794010 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4563. Min Act: -0.0002

Data Index: 1303035 (C4 (Web Text))

Max Activating Token Index: 136