Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1209162 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1041072 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0752. Min Act: -0.0002

Data Index: 164982 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0599. Min Act: -0.0002

Data Index: 171383 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1209345 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1201002 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0567. Min Act: -0.0002

Data Index: 263893 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0591. Min Act: -0.0002

Data Index: 225636 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0655. Min Act: -0.0002

Data Index: 758812 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0561. Min Act: -0.0002

Data Index: 50754 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1160918 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0593. Min Act: -0.0002

Data Index: 3167 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0571. Min Act: -0.0002

Data Index: 6763 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0553. Min Act: -0.0002

Data Index: 293820 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0515. Min Act: -0.0002

Data Index: 740953 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0561. Min Act: -0.0002

Data Index: 254113 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0580. Min Act: -0.0002

Data Index: 896016 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0538. Min Act: -0.0002

Data Index: 833421 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0520. Min Act: -0.0002

Data Index: 740587 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0506. Min Act: -0.0002

Data Index: 759681 (C4 (Web Text))

Max Activating Token Index: 249