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

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

Neuron 2914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7353. Min Range: -2.7353

Max Act: 2.7353. Min Act: -0.0000

Data Index: 1537508 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 2.7353. Min Range: -2.7353

Max Act: 2.1119. Min Act: -0.0000

Data Index: 1435409 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.9992. Min Act: -0.0000

Data Index: 1471601 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 2.7353. Min Range: -2.7353

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1374164 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.7356. Min Act: -0.0000

Data Index: 1563846 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1440088 (Python Code)

Max Activating Token Index: 772

Text #6

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1418067 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.6593. Min Act: -0.0000

Data Index: 1592798 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1380379 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.8266. Min Act: -0.0000

Data Index: 260431 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1451619 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1647309 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.5434. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1471929 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.5572. Min Act: -0.0000

Data Index: 1493798 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1541632 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.5498. Min Act: -0.0000

Data Index: 648012 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.5209. Min Act: -0.0000

Data Index: 604749 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1410248 (Python Code)

Max Activating Token Index: 805

Text #19

Max Range: 2.7353. Min Range: -2.7353

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1376999 (Python Code)

Max Activating Token Index: 302