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

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

Neuron 4012 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: 0.9178. Min Range: -0.9178

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1211376 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8935. Min Act: -0.0001

Data Index: 369801 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7016. Min Act: -0.0001

Data Index: 941350 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6808. Min Act: -0.0001

Data Index: 244707 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6522. Min Act: -0.0001

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1167710 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5974. Min Act: -0.0000

Data Index: 599395 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1048221 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1074823 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4934. Min Act: -0.0001

Data Index: 1034948 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4723. Min Act: -0.0001

Data Index: 1199190 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4668. Min Act: -0.0001

Data Index: 144606 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4629. Min Act: -0.0001

Data Index: 343128 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4911. Min Act: -0.0001

Data Index: 783527 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4732. Min Act: -0.0001

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4835. Min Act: -0.0001

Data Index: 961428 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4791. Min Act: -0.0000

Data Index: 249045 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4729. Min Act: -0.0000

Data Index: 338402 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4518. Min Act: -0.0001

Data Index: 392789 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.4356. Min Act: -0.0001

Data Index: 648495 (C4 (Web Text))

Max Activating Token Index: 212