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

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

Neuron 329 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.5734. Min Act: -0.0001

Data Index: 1288829 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0729. Min Act: -0.0001

Data Index: 136293 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.9449. Min Act: -0.0001

Data Index: 204331 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0714. Min Act: -0.0001

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0352. Min Act: -0.0001

Data Index: 174998 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0180. Min Act: -0.0001

Data Index: 224890 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.9931. Min Act: -0.0001

Data Index: 1335569 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.9759. Min Act: -0.0001

Data Index: 606833 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.9576. Min Act: -0.0001

Data Index: 579557 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.8061. Min Act: -0.0001

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.6732. Min Act: -0.0001

Data Index: 943297 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0675. Min Act: -0.0001

Data Index: 508741 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.8748. Min Act: -0.0001

Data Index: 997645 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0198. Min Act: -0.0001

Data Index: 129813 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.7393. Min Act: -0.0001

Data Index: 1274204 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.8647. Min Act: -0.0001

Data Index: 1129648 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.8594. Min Act: -0.0001

Data Index: 950488 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.5734. Min Range: -3.5734

Max Act: 3.0013. Min Act: -0.0001

Data Index: 853071 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.8458. Min Act: -0.0001

Data Index: 1128455 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.5734. Min Range: -3.5734

Max Act: 2.9844. Min Act: -0.0001

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 46