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

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

Neuron 1786 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: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0006

Data Index: 423545 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0495. Min Act: -0.0006

Data Index: 798292 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0496. Min Act: -0.0006

Data Index: 336602 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0496. Min Act: -0.0006

Data Index: 236614 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1273751 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0473. Min Act: -0.0006

Data Index: 240598 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0471. Min Act: -0.0006

Data Index: 338396 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0465. Min Act: -0.0006

Data Index: 1253293 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0455. Min Act: -0.0006

Data Index: 77790 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1088734 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1208922 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0463. Min Act: -0.0006

Data Index: 450497 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1171778 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1320443 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0458. Min Act: -0.0006

Data Index: 1233932 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0470. Min Act: -0.0006

Data Index: 263784 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0456. Min Act: -0.0006

Data Index: 1098026 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0466. Min Act: -0.0006

Data Index: 526531 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1273204 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0453. Min Act: -0.0006

Data Index: 756041 (C4 (Web Text))

Max Activating Token Index: 492