Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8926. Min Range: -2.8926

Max Act: 2.8926. Min Act: -0.0000

Data Index: 727552 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.9220. Min Act: -0.0000

Data Index: 149101 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.9968. Min Act: -0.0000

Data Index: 29632 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 2.8926. Min Range: -2.8926

Max Act: 2.0169. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 2.8926. Min Range: -2.8926

Max Act: 2.0568. Min Act: -0.0000

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.7329. Min Act: -0.0000

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.7302. Min Act: -0.0000

Data Index: 594371 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.6413. Min Act: -0.0000

Data Index: 176335 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.5539. Min Act: -0.0000

Data Index: 884605 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.5400. Min Act: -0.0000

Data Index: 1108508 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4575. Min Act: -0.0000

Data Index: 198907 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4233. Min Act: -0.0000

Data Index: 896094 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4966. Min Act: -0.0000

Data Index: 675185 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.6608. Min Act: -0.0000

Data Index: 745346 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.3216. Min Act: -0.0000

Data Index: 638116 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4688. Min Act: -0.0000

Data Index: 11692 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4646. Min Act: -0.0000

Data Index: 693092 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.5457. Min Act: -0.0000

Data Index: 199710 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.3540. Min Act: -0.0000

Data Index: 721972 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 2.8926. Min Range: -2.8926

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1126591 (C4 (Web Text))

Max Activating Token Index: 732