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

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

Neuron 4483 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.7951. Min Act: -0.0000

Data Index: 175015 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.3488. Min Act: -0.0000

Data Index: 293453 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.2703. Min Act: -0.0000

Data Index: 624902 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1132589 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1037176 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1151. Min Act: -0.0000

Data Index: 407148 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.2564. Min Act: -0.0000

Data Index: 542476 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1314786 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1134650 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1484. Min Act: -0.0000

Data Index: 674869 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1408. Min Act: -0.0000

Data Index: 290503 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1302239 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1103. Min Act: -0.0000

Data Index: 843095 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.0612. Min Act: -0.0000

Data Index: 65724 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.0180. Min Act: -0.0000

Data Index: 363879 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1023732 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1299. Min Act: -0.0000

Data Index: 152657 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.7951. Min Range: -1.7951

Max Act: 0.9933. Min Act: -0.0000

Data Index: 785350 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.7951. Min Range: -1.7951

Max Act: 1.1232. Min Act: -0.0000

Data Index: 432397 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 1.7951. Min Range: -1.7951

Max Act: 0.9453. Min Act: -0.0000

Data Index: 841122 (C4 (Web Text))

Max Activating Token Index: 823