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

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

Neuron 3596 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: 0.4724. Min Range: -0.4724

Max Act: 0.4724. Min Act: -0.0001

Data Index: 645240 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1035264 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3729. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.4080. Min Act: -0.0001

Data Index: 410344 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3343. Min Act: -0.0001

Data Index: 800642 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3091. Min Act: -0.0001

Data Index: 775023 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3569. Min Act: -0.0001

Data Index: 394422 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3159. Min Act: -0.0000

Data Index: 769231 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3217. Min Act: -0.0001

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3235. Min Act: -0.0000

Data Index: 972333 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2809. Min Act: -0.0001

Data Index: 714744 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3062. Min Act: -0.0001

Data Index: 35850 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2745. Min Act: -0.0001

Data Index: 88000 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2594. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2709. Min Act: -0.0001

Data Index: 998284 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2813. Min Act: -0.0000

Data Index: 204837 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2650. Min Act: -0.0000

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2364. Min Act: -0.0000

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2701. Min Act: -0.0000

Data Index: 591345 (C4 (Web Text))

Max Activating Token Index: 118