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

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

Neuron 676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.5967. Min Act: -0.0001

Data Index: 68555 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.4728. Min Act: -0.0001

Data Index: 1182477 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3771. Min Act: -0.0001

Data Index: 439419 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3842. Min Act: -0.0001

Data Index: 1159293 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3110. Min Act: -0.0001

Data Index: 927835 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3804. Min Act: -0.0001

Data Index: 1020841 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2561. Min Act: -0.0001

Data Index: 890309 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3827. Min Act: -0.0001

Data Index: 709517 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3271. Min Act: -0.0001

Data Index: 145725 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.3083. Min Act: -0.0001

Data Index: 187382 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2236. Min Act: -0.0001

Data Index: 787763 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.2231. Min Act: -0.0001

Data Index: 1171350 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1832. Min Act: -0.0001

Data Index: 913369 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1946. Min Act: -0.0001

Data Index: 206608 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1784. Min Act: -0.0001

Data Index: 1299805 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1567. Min Act: -0.0001

Data Index: 1326920 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1792. Min Act: -0.0001

Data Index: 238400 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.1079. Min Act: -0.0001

Data Index: 979157 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0427. Min Act: -0.0001

Data Index: 721330 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.5967. Min Range: -1.5967

Max Act: 1.0723. Min Act: -0.0001

Data Index: 187485 (C4 (Web Text))

Max Activating Token Index: 90