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

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

Neuron 1943 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5383. Min Act: -0.0000

Data Index: 838398 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5236. Min Act: -0.0000

Data Index: 688488 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1008981 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5300. Min Act: -0.0000

Data Index: 290161 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5150. Min Act: -0.0000

Data Index: 4619 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4913. Min Act: -0.0000

Data Index: 17653 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4466. Min Act: -0.0000

Data Index: 178137 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1200105 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3936. Min Act: -0.0000

Data Index: 741031 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3945. Min Act: -0.0000

Data Index: 275963 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3914. Min Act: -0.0000

Data Index: 467987 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4028. Min Act: -0.0000

Data Index: 226394 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3862. Min Act: -0.0000

Data Index: 378571 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3862. Min Act: -0.0000

Data Index: 578306 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3807. Min Act: -0.0000

Data Index: 914637 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1281473 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1298135 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3520. Min Act: -0.0000

Data Index: 250812 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1083989 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1245790 (C4 (Web Text))

Max Activating Token Index: 811