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

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

Neuron 1094 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0000

Data Index: 269801 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1737. Min Act: -0.0001

Data Index: 986396 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1602. Min Act: -0.0000

Data Index: 363907 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1075362 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1587. Min Act: -0.0001

Data Index: 841636 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1575. Min Act: -0.0000

Data Index: 763583 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1496. Min Act: -0.0000

Data Index: 830044 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1477. Min Act: -0.0000

Data Index: 273024 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1424. Min Act: 0.0000

Data Index: 361260 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1466. Min Act: -0.0000

Data Index: 670666 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1399. Min Act: -0.0001

Data Index: 530033 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1385. Min Act: -0.0000

Data Index: 485063 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1425. Min Act: 0.0004

Data Index: 1079205 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1419. Min Act: 0.0001

Data Index: 458415 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1362. Min Act: -0.0001

Data Index: 302644 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1229112 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1333. Min Act: -0.0001

Data Index: 71738 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1325. Min Act: -0.0000

Data Index: 397117 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1262. Min Act: -0.0000

Data Index: 247951 (C4 (Web Text))

Max Activating Token Index: 21