Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1141 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0001

Data Index: 307510 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1113. Min Act: -0.0001

Data Index: 598094 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1076. Min Act: -0.0001

Data Index: 24883 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0996. Min Act: -0.0001

Data Index: 941607 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0984. Min Act: -0.0001

Data Index: 833677 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0973. Min Act: -0.0001

Data Index: 978397 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0857. Min Act: -0.0001

Data Index: 739081 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0951. Min Act: -0.0001

Data Index: 148054 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0980. Min Act: -0.0001

Data Index: 41947 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0969. Min Act: -0.0001

Data Index: 910596 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0879. Min Act: -0.0001

Data Index: 620380 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1061939 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0948. Min Act: -0.0001

Data Index: 383100 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0941. Min Act: -0.0001

Data Index: 962484 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0911. Min Act: -0.0001

Data Index: 923151 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0940. Min Act: -0.0001

Data Index: 703576 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0763. Min Act: -0.0001

Data Index: 667661 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0897. Min Act: -0.0001

Data Index: 691262 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0898. Min Act: -0.0001

Data Index: 14570 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0878. Min Act: -0.0001

Data Index: 592432 (C4 (Web Text))

Max Activating Token Index: 723