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

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

Neuron 4380 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0000

Data Index: 442063 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1066360 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3419. Min Act: -0.0000

Data Index: 391777 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1161780 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1264405 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3229. Min Act: -0.0000

Data Index: 314621 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3386. Min Act: -0.0000

Data Index: 392657 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2919. Min Act: -0.0000

Data Index: 220717 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1329049 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2822. Min Act: -0.0000

Data Index: 433510 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2896. Min Act: -0.0000

Data Index: 484673 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1225968 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2954. Min Act: -0.0000

Data Index: 928191 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1301673 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1239369 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2926. Min Act: -0.0000

Data Index: 41797 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2544. Min Act: -0.0000

Data Index: 933576 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2729. Min Act: -0.0000

Data Index: 789255 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1201685 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1207261 (C4 (Web Text))

Max Activating Token Index: 889