Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1334232 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0619. Min Act: -0.0001

Data Index: 65218 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1208923 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0533. Min Act: -0.0001

Data Index: 418893 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0491. Min Act: -0.0001

Data Index: 2784 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0484. Min Act: -0.0001

Data Index: 103812 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1332675 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1176279 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0513. Min Act: -0.0001

Data Index: 518063 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1027009 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0463. Min Act: -0.0001

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1240861 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0407. Min Act: -0.0001

Data Index: 663071 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0460. Min Act: -0.0001

Data Index: 819944 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1285647 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1321284 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0426. Min Act: -0.0001

Data Index: 312157 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0408. Min Act: -0.0001

Data Index: 786877 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0440. Min Act: -0.0001

Data Index: 454003 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0399. Min Act: -0.0001

Data Index: 98806 (C4 (Web Text))

Max Activating Token Index: 646