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

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

Neuron 422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1266634 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2107. Min Act: -0.0001

Data Index: 459122 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1946. Min Act: -0.0001

Data Index: 101362 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1239008 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1734. Min Act: -0.0000

Data Index: 232623 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1723. Min Act: -0.0000

Data Index: 165831 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1227823 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1573. Min Act: -0.0000

Data Index: 505414 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1634. Min Act: -0.0000

Data Index: 814930 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1571. Min Act: -0.0000

Data Index: 908220 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1543. Min Act: -0.0000

Data Index: 394475 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1267873 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1482. Min Act: -0.0000

Data Index: 748556 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1618. Min Act: -0.0000

Data Index: 443669 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1374. Min Act: -0.0000

Data Index: 788370 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1408. Min Act: -0.0000

Data Index: 931270 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1493. Min Act: -0.0000

Data Index: 205402 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1439. Min Act: -0.0001

Data Index: 479794 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1416. Min Act: -0.0000

Data Index: 830820 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1161021 (C4 (Web Text))

Max Activating Token Index: 569