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

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

Neuron 120 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.3871. Min Act: -0.0001

Data Index: 1113112 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0673. Min Act: -0.0001

Data Index: 982809 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1329. Min Act: -0.0001

Data Index: 194648 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1989. Min Act: -0.0001

Data Index: 493745 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0753. Min Act: -0.0001

Data Index: 560457 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9511. Min Act: -0.0001

Data Index: 134225 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9936. Min Act: -0.0001

Data Index: 137597 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0911. Min Act: -0.0001

Data Index: 351164 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0745. Min Act: -0.0001

Data Index: 557469 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.2009. Min Act: -0.0001

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.1664. Min Act: -0.0001

Data Index: 1319185 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0355. Min Act: -0.0001

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9601. Min Act: -0.0001

Data Index: 462366 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0590. Min Act: -0.0001

Data Index: 1094950 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9706. Min Act: -0.0001

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0291. Min Act: -0.0001

Data Index: 1149687 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.3871. Min Range: -1.3871

Max Act: 1.0255. Min Act: -0.0001

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9329. Min Act: -0.0001

Data Index: 310066 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9465. Min Act: -0.0001

Data Index: 517018 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.3871. Min Range: -1.3871

Max Act: 0.9766. Min Act: -0.0001

Data Index: 813584 (C4 (Web Text))

Max Activating Token Index: 611