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

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

Neuron 2240 in Layer 0

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: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 932980 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1009. Min Act: -0.0001

Data Index: 991865 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0998. Min Act: -0.0001

Data Index: 515351 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1120057 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0962. Min Act: -0.0001

Data Index: 191364 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1121677 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1349596 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0921. Min Act: -0.0001

Data Index: 900758 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0906. Min Act: -0.0001

Data Index: 268591 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0902. Min Act: -0.0001

Data Index: 748762 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0877. Min Act: -0.0001

Data Index: 742126 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0849. Min Act: -0.0001

Data Index: 577119 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0833. Min Act: -0.0001

Data Index: 993604 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0816. Min Act: -0.0001

Data Index: 379519 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0786. Min Act: -0.0001

Data Index: 109553 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0781. Min Act: -0.0001

Data Index: 785071 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0796. Min Act: -0.0001

Data Index: 693856 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0753. Min Act: -0.0001

Data Index: 233607 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0745. Min Act: -0.0001

Data Index: 301334 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0729. Min Act: -0.0001

Data Index: 183766 (C4 (Web Text))

Max Activating Token Index: 501