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

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

Neuron 2554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.5326. Min Act: -0.0000

Data Index: 1315576 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4421. Min Act: -0.0000

Data Index: 714474 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.5368. Min Act: -0.0000

Data Index: 594756 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.5994. Min Act: -0.0000

Data Index: 604934 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4390. Min Act: -0.0000

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4351. Min Act: -0.0000

Data Index: 529741 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.1443. Min Act: -0.0000

Data Index: 679654 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.2449. Min Act: -0.0000

Data Index: 98100 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.5486. Min Act: -0.0000

Data Index: 749448 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.5266. Min Act: -0.0000

Data Index: 1210799 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4849. Min Act: -0.0000

Data Index: 418028 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4505. Min Act: -0.0000

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.3032. Min Act: -0.0000

Data Index: 21781 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.4550. Min Act: -0.0000

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.2531. Min Act: -0.0000

Data Index: 580290 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.1538. Min Act: -0.0000

Data Index: 232569 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.1706. Min Act: -0.0000

Data Index: 85176 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.0419. Min Act: -0.0000

Data Index: 545096 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.5994. Min Range: -3.5994

Max Act: 3.2722. Min Act: -0.0000

Data Index: 1217431 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 3.5994. Min Range: -3.5994

Max Act: 2.9945. Min Act: -0.0000

Data Index: 176501 (C4 (Web Text))

Max Activating Token Index: 686