Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1384082 (Python Code)

Max Activating Token Index: 344

Text #1

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.4364. Min Act: -0.0000

Data Index: 154702 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1491647 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.5078. Min Act: -0.0000

Data Index: 157799 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1443193 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1650188 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.4539. Min Act: -0.0000

Data Index: 1378841 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3600. Min Act: -0.0000

Data Index: 402636 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1254944 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1390012 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3640. Min Act: -0.0000

Data Index: 554814 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1563144 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1253319 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1520518 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3275. Min Act: -0.0000

Data Index: 316392 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.2815. Min Act: -0.0000

Data Index: 290941 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1642616 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.3048. Min Act: -0.0000

Data Index: 478890 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1052431 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.6499. Min Range: -1.6499

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1318519 (C4 (Web Text))

Max Activating Token Index: 548