Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2504 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1482824 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1200582 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1766. Min Act: -0.0001

Data Index: 978934 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1809. Min Act: -0.0000

Data Index: 635625 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1634. Min Act: -0.0000

Data Index: 147178 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1124172 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1708. Min Act: -0.0000

Data Index: 291099 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1424. Min Act: -0.0000

Data Index: 155153 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1606. Min Act: -0.0001

Data Index: 307531 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1562217 (Python Code)

Max Activating Token Index: 962

Text #10

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1368631 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1494. Min Act: -0.0000

Data Index: 330897 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1445. Min Act: -0.0001

Data Index: 126977 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1440. Min Act: -0.0001

Data Index: 458253 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1014223 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1338. Min Act: -0.0000

Data Index: 199945 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1416. Min Act: -0.0001

Data Index: 726924 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1407975 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1363. Min Act: -0.0001

Data Index: 507765 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1513487 (Python Code)

Max Activating Token Index: 887