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

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

Neuron 1007 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2942. Min Act: -0.0000

Data Index: 956713 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2658. Min Act: -0.0000

Data Index: 262464 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2273. Min Act: -0.0001

Data Index: 585360 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.2109. Min Act: -0.0000

Data Index: 648924 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1884. Min Act: -0.0001

Data Index: 700932 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1973. Min Act: -0.0000

Data Index: 534378 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1908. Min Act: -0.0000

Data Index: 866895 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1822. Min Act: -0.0000

Data Index: 394090 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1778. Min Act: -0.0000

Data Index: 932263 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1067239 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1725. Min Act: -0.0001

Data Index: 209553 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1651. Min Act: -0.0000

Data Index: 423105 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1744. Min Act: -0.0001

Data Index: 542257 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1609. Min Act: -0.0000

Data Index: 91808 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1662. Min Act: -0.0001

Data Index: 64547 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1613. Min Act: -0.0000

Data Index: 779465 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1008430 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1620. Min Act: -0.0001

Data Index: 885838 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1594. Min Act: -0.0000

Data Index: 93496 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.2942. Min Range: -0.2942

Max Act: 0.1569. Min Act: -0.0001

Data Index: 889462 (C4 (Web Text))

Max Activating Token Index: 681