Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5925. Min Act: -0.0000

Data Index: 389006 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1069881 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.3694. Min Act: -0.0000

Data Index: 913696 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.2950. Min Act: -0.0000

Data Index: 221932 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.1596. Min Act: -0.0000

Data Index: 362763 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1213710 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.2516. Min Act: -0.0000

Data Index: 242397 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1166926 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0841. Min Act: -0.0000

Data Index: 4445 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0840. Min Act: -0.0000

Data Index: 810349 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1332249 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0137. Min Act: -0.0000

Data Index: 644457 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1135611 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0666. Min Act: -0.0000

Data Index: 845020 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1100402 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1127299 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 1.5925. Min Range: -1.5925

Max Act: 0.9461. Min Act: -0.0000

Data Index: 190456 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0493. Min Act: -0.0000

Data Index: 335044 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.0459. Min Act: -0.0000

Data Index: 716196 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.2049. Min Act: -0.0000

Data Index: 665031 (C4 (Web Text))

Max Activating Token Index: 862