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

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

Neuron 4346 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: 0.6153. Min Range: -0.6153

Max Act: 0.6153. Min Act: -0.0000

Data Index: 959829 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.5696. Min Act: -0.0000

Data Index: 407997 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.5249. Min Act: -0.0000

Data Index: 311527 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1569172 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4474. Min Act: -0.0000

Data Index: 67836 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4243. Min Act: -0.0000

Data Index: 632842 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3959. Min Act: -0.0000

Data Index: 303124 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4061. Min Act: -0.0000

Data Index: 920988 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4050. Min Act: -0.0000

Data Index: 234136 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1298537 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4000. Min Act: -0.0000

Data Index: 472557 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3919. Min Act: -0.0000

Data Index: 968201 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1172042 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3808. Min Act: -0.0000

Data Index: 400291 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3579. Min Act: -0.0000

Data Index: 336679 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3932. Min Act: -0.0000

Data Index: 192914 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3790. Min Act: -0.0000

Data Index: 101433 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3670. Min Act: -0.0000

Data Index: 899911 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3545. Min Act: -0.0000

Data Index: 510154 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1176959 (C4 (Web Text))

Max Activating Token Index: 659