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

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

Neuron 3377 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0000

Data Index: 195301 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2226. Min Act: -0.0000

Data Index: 220851 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2017. Min Act: -0.0000

Data Index: 442845 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2025. Min Act: -0.0000

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1058796 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2078. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2044. Min Act: -0.0000

Data Index: 518583 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1968. Min Act: -0.0000

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1223761 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1123676 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1967. Min Act: -0.0000

Data Index: 113092 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1970. Min Act: -0.0000

Data Index: 390492 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1954. Min Act: -0.0000

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1543349 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1879. Min Act: -0.0000

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1163203 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1889. Min Act: -0.0000

Data Index: 792960 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1841. Min Act: -0.0000

Data Index: 975226 (C4 (Web Text))

Max Activating Token Index: 543