Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 836 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0005

Data Index: 302680 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0597. Min Act: -0.0006

Data Index: 315059 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0554. Min Act: -0.0006

Data Index: 630666 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0571. Min Act: -0.0006

Data Index: 442678 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1125111 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0538. Min Act: -0.0006

Data Index: 787053 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0517. Min Act: -0.0006

Data Index: 277748 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0497. Min Act: -0.0006

Data Index: 912415 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0504. Min Act: -0.0006

Data Index: 700183 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0465. Min Act: -0.0006

Data Index: 939062 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1085038 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0500. Min Act: -0.0006

Data Index: 1287763 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1310958 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0462. Min Act: -0.0006

Data Index: 1032763 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0448. Min Act: -0.0006

Data Index: 1008123 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0407. Min Act: -0.0006

Data Index: 557709 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0452. Min Act: -0.0005

Data Index: 709862 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0471. Min Act: -0.0006

Data Index: 732678 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0450. Min Act: -0.0006

Data Index: 1296657 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0449. Min Act: -0.0006

Data Index: 855901 (C4 (Web Text))

Max Activating Token Index: 726