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

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

Neuron 5652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.6449. Min Act: -0.0000

Data Index: 1023495 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1292485 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.6455. Min Act: -0.0000

Data Index: 50225 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.5010. Min Act: -0.0000

Data Index: 1247513 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4599. Min Act: -0.0000

Data Index: 594646 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4783. Min Act: -0.0000

Data Index: 433836 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4127. Min Act: -0.0000

Data Index: 883859 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.5104. Min Act: -0.0000

Data Index: 754355 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1036734 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3228. Min Act: -0.0000

Data Index: 881148 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1019993 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4293. Min Act: -0.0000

Data Index: 387916 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3729. Min Act: -0.0000

Data Index: 22816 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3698. Min Act: -0.0000

Data Index: 817845 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3865. Min Act: -0.0000

Data Index: 689029 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1177031 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3869. Min Act: -0.0000

Data Index: 970368 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.4150. Min Act: -0.0000

Data Index: 999914 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1227885 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 1.6455. Min Range: -1.6455

Max Act: 1.3278. Min Act: -0.0000

Data Index: 940429 (C4 (Web Text))

Max Activating Token Index: 153