Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 719 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1743. Min Act: -0.0003

Data Index: 815145 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1529. Min Act: -0.0003

Data Index: 540031 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1509. Min Act: -0.0003

Data Index: 1239902 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1594. Min Act: -0.0003

Data Index: 630820 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1456. Min Act: -0.0003

Data Index: 481509 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1471. Min Act: -0.0003

Data Index: 178063 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1495. Min Act: -0.0003

Data Index: 427638 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1437. Min Act: -0.0003

Data Index: 38617 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1487. Min Act: -0.0003

Data Index: 287802 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1410. Min Act: -0.0003

Data Index: 759150 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1407. Min Act: -0.0003

Data Index: 360535 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1464. Min Act: -0.0003

Data Index: 745056 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1401. Min Act: -0.0003

Data Index: 874529 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1445. Min Act: -0.0003

Data Index: 510325 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1378. Min Act: -0.0003

Data Index: 1240144 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1309. Min Act: -0.0003

Data Index: 1269584 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1404. Min Act: -0.0003

Data Index: 745800 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1290. Min Act: -0.0003

Data Index: 917018 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1277. Min Act: -0.0003

Data Index: 550698 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1205. Min Act: -0.0003

Data Index: 199143 (C4 (Web Text))

Max Activating Token Index: 591