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

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

Neuron 2179 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0001

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2473. Min Act: -0.0000

Data Index: 589319 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1312996 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2048. Min Act: -0.0001

Data Index: 497025 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1985. Min Act: -0.0001

Data Index: 819103 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2038. Min Act: -0.0001

Data Index: 27785 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2150. Min Act: -0.0000

Data Index: 857215 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1222150 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2165. Min Act: -0.0001

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2044. Min Act: -0.0000

Data Index: 6152 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2116. Min Act: -0.0001

Data Index: 31394 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2010. Min Act: -0.0001

Data Index: 391541 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1948. Min Act: -0.0000

Data Index: 712691 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1924. Min Act: -0.0001

Data Index: 716986 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1862. Min Act: -0.0000

Data Index: 617352 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1829. Min Act: -0.0001

Data Index: 508186 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1951. Min Act: -0.0000

Data Index: 186204 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1922. Min Act: -0.0001

Data Index: 242723 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1892. Min Act: -0.0000

Data Index: 108022 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1819. Min Act: -0.0001

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 680