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

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

Neuron 3514 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: 2.4534. Min Range: -2.4534

Max Act: 2.4005. Min Act: -0.0000

Data Index: 641892 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.1165. Min Act: -0.0000

Data Index: 118660 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.4534. Min Act: -0.0000

Data Index: 244999 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.3224. Min Act: -0.0000

Data Index: 1351516 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.2471. Min Act: -0.0000

Data Index: 1113211 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.1725. Min Act: -0.0000

Data Index: 168895 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.2677. Min Act: -0.0001

Data Index: 336346 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.0522. Min Act: -0.0000

Data Index: 481952 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.1771. Min Act: -0.0000

Data Index: 630080 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 2.4534. Min Range: -2.4534

Max Act: 2.0202. Min Act: -0.0000

Data Index: 696445 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.6950. Min Act: -0.0000

Data Index: 482174 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.9412. Min Act: -0.0000

Data Index: 389785 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.9095. Min Act: -0.0000

Data Index: 540494 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.8988. Min Act: -0.0000

Data Index: 585575 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.9569. Min Act: -0.0000

Data Index: 368314 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.8060. Min Act: -0.0000

Data Index: 1358892 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.8814. Min Act: -0.0000

Data Index: 497923 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.7825. Min Act: -0.0001

Data Index: 570230 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.6830. Min Act: -0.0001

Data Index: 725355 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 2.4534. Min Range: -2.4534

Max Act: 1.6686. Min Act: -0.0000

Data Index: 220564 (C4 (Web Text))

Max Activating Token Index: 718