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

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

Neuron 1831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1319038 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1179844 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4982. Min Act: -0.0000

Data Index: 386915 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.4258. Min Act: -0.0000

Data Index: 28774 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3920. Min Act: -0.0000

Data Index: 500962 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3994. Min Act: -0.0000

Data Index: 804763 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3694. Min Act: -0.0000

Data Index: 452479 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3445. Min Act: -0.0000

Data Index: 246607 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3383. Min Act: -0.0000

Data Index: 857497 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3621. Min Act: -0.0000

Data Index: 444847 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.2585. Min Act: -0.0000

Data Index: 932516 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3496. Min Act: -0.0000

Data Index: 89600 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3322. Min Act: -0.0000

Data Index: 386617 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3292. Min Act: -0.0000

Data Index: 789278 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3279. Min Act: -0.0000

Data Index: 185088 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3277. Min Act: -0.0000

Data Index: 2512 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3107. Min Act: -0.0000

Data Index: 294911 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3251. Min Act: -0.0000

Data Index: 364702 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3196. Min Act: -0.0000

Data Index: 815696 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.5887. Min Range: -0.5887

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 803