Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1366 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0500. Min Act: -0.0002

Data Index: 740337 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0478. Min Act: -0.0002

Data Index: 668686 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0480. Min Act: -0.0002

Data Index: 774896 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0477. Min Act: -0.0002

Data Index: 604817 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0473. Min Act: -0.0002

Data Index: 729727 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1198586 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0464. Min Act: -0.0002

Data Index: 939856 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0459. Min Act: -0.0002

Data Index: 755959 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0449. Min Act: -0.0002

Data Index: 730291 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0460. Min Act: -0.0002

Data Index: 648715 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1265359 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0444. Min Act: -0.0002

Data Index: 127876 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0440. Min Act: -0.0002

Data Index: 148802 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0442. Min Act: -0.0002

Data Index: 882392 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0443. Min Act: -0.0002

Data Index: 62305 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0444. Min Act: -0.0002

Data Index: 551178 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1067437 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1010862 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1089703 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1102110 (C4 (Web Text))

Max Activating Token Index: 96