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

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

Neuron 4250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.7154. Min Act: -0.0000

Data Index: 917339 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1142356 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6645. Min Act: -0.0000

Data Index: 744722 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5991. Min Act: -0.0000

Data Index: 831781 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6031. Min Act: -0.0000

Data Index: 301559 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5947. Min Act: -0.0000

Data Index: 621695 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1312548 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5896. Min Act: -0.0000

Data Index: 751862 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5822. Min Act: -0.0000

Data Index: 756270 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6029. Min Act: -0.0000

Data Index: 806564 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5385. Min Act: -0.0000

Data Index: 710946 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1359761 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5066. Min Act: -0.0000

Data Index: 543569 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1203106 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5343. Min Act: -0.0000

Data Index: 730725 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1005005 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1317439 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4921. Min Act: -0.0000

Data Index: 256323 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5072. Min Act: -0.0000

Data Index: 517493 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4893. Min Act: -0.0000

Data Index: 970827 (C4 (Web Text))

Max Activating Token Index: 138