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

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

Neuron 1541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1318316 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5823. Min Act: -0.0000

Data Index: 896054 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5749. Min Act: -0.0000

Data Index: 986413 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5390. Min Act: -0.0001

Data Index: 637942 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5453. Min Act: -0.0000

Data Index: 765516 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5280. Min Act: -0.0000

Data Index: 303929 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1211554 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5211. Min Act: -0.0001

Data Index: 935293 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.5555. Min Act: -0.0000

Data Index: 568286 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4628. Min Act: -0.0000

Data Index: 454330 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4865. Min Act: -0.0000

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4475. Min Act: -0.0001

Data Index: 835919 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4679. Min Act: -0.0001

Data Index: 48038 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4739. Min Act: -0.0000

Data Index: 563107 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4462. Min Act: -0.0000

Data Index: 377722 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4504. Min Act: -0.0001

Data Index: 938670 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4367. Min Act: -0.0000

Data Index: 779075 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4727. Min Act: -0.0000

Data Index: 417271 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4547. Min Act: -0.0001

Data Index: 1089349 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.6724. Min Range: -0.6724

Max Act: 0.4210. Min Act: -0.0000

Data Index: 435050 (C4 (Web Text))

Max Activating Token Index: 872