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

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

Neuron 939 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1467. Min Act: -0.0002

Data Index: 319695 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1106. Min Act: -0.0001

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1052. Min Act: -0.0002

Data Index: 528425 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1055. Min Act: -0.0002

Data Index: 903694 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1194435 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0988. Min Act: -0.0001

Data Index: 829834 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0930. Min Act: -0.0002

Data Index: 94177 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1485 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0969. Min Act: -0.0002

Data Index: 152868 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1003. Min Act: -0.0002

Data Index: 981300 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0929. Min Act: -0.0001

Data Index: 133213 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0955. Min Act: -0.0002

Data Index: 688151 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0887. Min Act: -0.0002

Data Index: 422143 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0912. Min Act: -0.0001

Data Index: 17695 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0871. Min Act: -0.0001

Data Index: 71219 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0902. Min Act: -0.0001

Data Index: 159056 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0884. Min Act: -0.0001

Data Index: 490864 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0975. Min Act: -0.0002

Data Index: 711489 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0900. Min Act: -0.0001

Data Index: 816613 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0911. Min Act: -0.0001

Data Index: 851514 (C4 (Web Text))

Max Activating Token Index: 817