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

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

Neuron 638 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.3477. Min Act: 0.0000

Data Index: 846663 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1104898 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0059. Min Act: -0.0000

Data Index: 391895 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9753. Min Act: 0.0001

Data Index: 775386 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9618. Min Act: 0.0000

Data Index: 778664 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9845. Min Act: -0.0000

Data Index: 683229 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9459. Min Act: 0.0000

Data Index: 812301 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8564. Min Act: 0.0000

Data Index: 231567 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8903. Min Act: 0.0000

Data Index: 818884 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1337297 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.9028. Min Act: -0.0000

Data Index: 856849 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8536. Min Act: -0.0000

Data Index: 301520 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1269479 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.7930. Min Act: 0.0000

Data Index: 825409 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8333. Min Act: -0.0000

Data Index: 733939 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8314. Min Act: 0.0000

Data Index: 200569 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.7973. Min Act: 0.0002

Data Index: 161384 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8457. Min Act: 0.0000

Data Index: 145160 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.8040. Min Act: 0.0000

Data Index: 1265890 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.3477. Min Range: -1.3477

Max Act: 0.7479. Min Act: 0.0000

Data Index: 355309 (C4 (Web Text))

Max Activating Token Index: 268