Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5420 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1040171 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0664. Min Act: -0.0002

Data Index: 165003 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0588. Min Act: -0.0002

Data Index: 410224 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0606. Min Act: -0.0002

Data Index: 171988 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0604. Min Act: -0.0002

Data Index: 211689 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0539. Min Act: -0.0002

Data Index: 772546 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0518. Min Act: -0.0002

Data Index: 641535 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0534. Min Act: -0.0002

Data Index: 484654 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0521. Min Act: -0.0002

Data Index: 683671 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1236737 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0501. Min Act: -0.0002

Data Index: 146567 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1232788 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0517. Min Act: -0.0002

Data Index: 632941 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1050467 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1175871 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1043494 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1013675 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1498 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0430. Min Act: -0.0002

Data Index: 563476 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1252967 (C4 (Web Text))

Max Activating Token Index: 479