Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0006

Data Index: 1168520 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0551. Min Act: -0.0006

Data Index: 848551 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0547. Min Act: -0.0006

Data Index: 246005 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0547. Min Act: -0.0006

Data Index: 1065097 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0545. Min Act: -0.0006

Data Index: 57877 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0542. Min Act: -0.0006

Data Index: 115784 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0515. Min Act: -0.0006

Data Index: 1270030 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0523. Min Act: -0.0006

Data Index: 1030262 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0511. Min Act: -0.0006

Data Index: 1179143 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0516. Min Act: -0.0006

Data Index: 80950 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0492. Min Act: -0.0006

Data Index: 928041 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1140900 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1011837 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0506. Min Act: -0.0006

Data Index: 98322 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0504. Min Act: -0.0006

Data Index: 1176463 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1348430 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0502. Min Act: -0.0006

Data Index: 550979 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0491. Min Act: -0.0006

Data Index: 775290 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0500. Min Act: -0.0006

Data Index: 1258123 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0497. Min Act: -0.0006

Data Index: 576015 (C4 (Web Text))

Max Activating Token Index: 518