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

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

Neuron 1825 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0000

Data Index: 729620 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0897. Min Act: -0.0001

Data Index: 305818 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0831. Min Act: -0.0000

Data Index: 615524 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0871. Min Act: -0.0000

Data Index: 642312 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0863. Min Act: -0.0000

Data Index: 887937 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0827. Min Act: -0.0000

Data Index: 944944 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1123715 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0854. Min Act: -0.0001

Data Index: 585811 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0851. Min Act: -0.0001

Data Index: 481671 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0835. Min Act: -0.0000

Data Index: 66735 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0855. Min Act: -0.0000

Data Index: 334164 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0822. Min Act: -0.0001

Data Index: 911319 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1441785 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0803. Min Act: -0.0000

Data Index: 691329 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0818. Min Act: -0.0001

Data Index: 164685 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0819. Min Act: -0.0001

Data Index: 646458 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0724. Min Act: -0.0001

Data Index: 296012 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0789. Min Act: -0.0001

Data Index: 319721 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0782. Min Act: -0.0000

Data Index: 315931 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1024658 (C4 (Web Text))

Max Activating Token Index: 257