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

Dataset: The Pile

Neuron 5076 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.8126. Min Act: -0.0000

Data Index: 207790 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.9297. Min Act: -0.0000

Data Index: 832454 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1474050 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.7522. Min Act: -0.0000

Data Index: 1904815 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1174945 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1836245 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1417106 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5563. Min Act: -0.0000

Data Index: 195424 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1635758 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5864. Min Act: -0.0000

Data Index: 552754 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5912. Min Act: -0.0000

Data Index: 988701 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5777. Min Act: -0.0000

Data Index: 191773 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5760. Min Act: -0.0000

Data Index: 680454 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1397054 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5674. Min Act: -0.0000

Data Index: 613914 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.4797. Min Act: -0.0000

Data Index: 536274 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.6398. Min Act: -0.0000

Data Index: 1002171 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5381. Min Act: -0.0000

Data Index: 74139 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5524. Min Act: -0.0000

Data Index: 92058 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.9297. Min Range: -1.9297

Max Act: 1.5468. Min Act: -0.0000

Data Index: 941381 (The Pile)

Max Activating Token Index: 559