Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2483 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4634. Min Act: -0.0001

Data Index: 592936 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4190. Min Act: -0.0001

Data Index: 927843 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.4021. Min Act: -0.0001

Data Index: 1119281 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3720. Min Act: -0.0001

Data Index: 87842 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1267341 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.3200. Min Act: -0.0001

Data Index: 257549 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2846. Min Act: -0.0001

Data Index: 490658 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2823. Min Act: -0.0001

Data Index: 179754 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1278364 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2676. Min Act: -0.0001

Data Index: 389462 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2743. Min Act: -0.0001

Data Index: 410295 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2607. Min Act: -0.0001

Data Index: 268049 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1329317 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2405. Min Act: -0.0001

Data Index: 770248 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2489. Min Act: -0.0001

Data Index: 923017 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2567. Min Act: -0.0001

Data Index: 160464 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2565. Min Act: -0.0001

Data Index: 998322 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1335839 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1016927 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.4634. Min Range: -0.4634

Max Act: 0.2547. Min Act: -0.0001

Data Index: 846761 (C4 (Web Text))

Max Activating Token Index: 9