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

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

Neuron 2358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4449. Min Act: -0.0001

Data Index: 916376 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1290247 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4760. Min Act: -0.0001

Data Index: 646725 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4184. Min Act: -0.0001

Data Index: 389916 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4329. Min Act: -0.0001

Data Index: 347623 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4317. Min Act: -0.0001

Data Index: 837283 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3870. Min Act: -0.0001

Data Index: 335291 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4119. Min Act: -0.0001

Data Index: 824524 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1335079 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3712. Min Act: -0.0001

Data Index: 1267984 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.4236. Min Act: -0.0000

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3811. Min Act: -0.0000

Data Index: 594064 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1331499 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3914. Min Act: -0.0000

Data Index: 714947 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3729. Min Act: -0.0001

Data Index: 467331 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3749. Min Act: -0.0001

Data Index: 701018 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1202258 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3677. Min Act: -0.0001

Data Index: 687959 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1027416 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.4760. Min Range: -0.4760

Max Act: 0.3879. Min Act: -0.0001

Data Index: 1070912 (C4 (Web Text))

Max Activating Token Index: 513