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

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

Neuron 5103 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: 0.1748. Min Range: -0.1748

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1343229 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0001

Data Index: 889128 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1541. Min Act: -0.0001

Data Index: 546642 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1351479 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1111945 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1579. Min Act: -0.0001

Data Index: 829129 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1531. Min Act: -0.0001

Data Index: 180685 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1463. Min Act: -0.0001

Data Index: 280841 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1070935 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1480. Min Act: -0.0001

Data Index: 782324 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1329. Min Act: -0.0001

Data Index: 95475 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1077806 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1348. Min Act: -0.0001

Data Index: 850481 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1009190 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1245. Min Act: -0.0001

Data Index: 661091 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1313156 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1296. Min Act: -0.0001

Data Index: 901686 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1439. Min Act: -0.0001

Data Index: 711156 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1348. Min Act: -0.0001

Data Index: 172412 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1309. Min Act: -0.0001

Data Index: 349335 (C4 (Web Text))

Max Activating Token Index: 831