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

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

Neuron 2564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0001

Data Index: 584904 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1177050 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0496. Min Act: -0.0001

Data Index: 712201 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1547918 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0433. Min Act: -0.0001

Data Index: 689899 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0451. Min Act: -0.0001

Data Index: 729008 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0434. Min Act: -0.0001

Data Index: 421556 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0466. Min Act: -0.0001

Data Index: 530316 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0424. Min Act: -0.0001

Data Index: 871161 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0433. Min Act: -0.0001

Data Index: 313762 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1463051 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0406. Min Act: -0.0001

Data Index: 857091 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0422. Min Act: -0.0001

Data Index: 152957 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0436. Min Act: -0.0001

Data Index: 943677 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1649226 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0427. Min Act: -0.0001

Data Index: 516231 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1136717 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1132880 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1235379 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1308912 (C4 (Web Text))

Max Activating Token Index: 689