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

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

Neuron 3604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0000

Data Index: 442284 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2313. Min Act: -0.0000

Data Index: 360735 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2173. Min Act: -0.0000

Data Index: 733818 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1269742 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1299677 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2100. Min Act: -0.0000

Data Index: 581107 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1958. Min Act: -0.0000

Data Index: 157651 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2027. Min Act: -0.0000

Data Index: 581817 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1219237 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1988. Min Act: -0.0000

Data Index: 735118 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1966. Min Act: -0.0000

Data Index: 763805 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1812. Min Act: -0.0001

Data Index: 621193 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1773. Min Act: -0.0000

Data Index: 260478 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1839. Min Act: -0.0000

Data Index: 652859 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1799. Min Act: -0.0000

Data Index: 927964 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1188963 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1768. Min Act: -0.0000

Data Index: 240388 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1763. Min Act: -0.0000

Data Index: 131249 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1757. Min Act: -0.0000

Data Index: 931049 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1706. Min Act: -0.0000

Data Index: 403133 (C4 (Web Text))

Max Activating Token Index: 28