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

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

Neuron 1269 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0002

Data Index: 1028521 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0576. Min Act: -0.0002

Data Index: 131387 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0272. Min Act: -0.0002

Data Index: 458370 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9883. Min Act: -0.0002

Data Index: 748090 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0173. Min Act: -0.0002

Data Index: 142604 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9958. Min Act: -0.0002

Data Index: 839433 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9822. Min Act: -0.0002

Data Index: 19552 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9841. Min Act: -0.0002

Data Index: 879917 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9877. Min Act: -0.0002

Data Index: 235602 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9674. Min Act: -0.0002

Data Index: 180042 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9871. Min Act: -0.0002

Data Index: 596239 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9652. Min Act: -0.0002

Data Index: 709205 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9850. Min Act: -0.0002

Data Index: 375237 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9779. Min Act: -0.0002

Data Index: 49660 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9832. Min Act: -0.0003

Data Index: 801950 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9886. Min Act: -0.0002

Data Index: 1125016 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9645. Min Act: -0.0002

Data Index: 391135 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9607. Min Act: -0.0002

Data Index: 1012041 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9545. Min Act: -0.0002

Data Index: 948597 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9587. Min Act: -0.0002

Data Index: 478650 (C4 (Web Text))

Max Activating Token Index: 916