Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 350 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 856036 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 943170 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0170. Min Act: -0.0006

Data Index: 449105 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0173. Min Act: -0.0005

Data Index: 814280 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0171. Min Act: -0.0006

Data Index: 572398 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0171. Min Act: -0.0006

Data Index: 518588 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1057350 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0170. Min Act: -0.0006

Data Index: 91246 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0169. Min Act: -0.0006

Data Index: 318550 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1151841 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0169. Min Act: -0.0006

Data Index: 924654 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1271261 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 130365 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 389749 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 503998 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1145649 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0006

Data Index: 646412 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0163. Min Act: -0.0006

Data Index: 868681 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0006

Data Index: 77736 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0006

Data Index: 838581 (C4 (Web Text))

Max Activating Token Index: 696