Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 445 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.1329. Min Act: -0.0001

Data Index: 609456 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.0038. Min Act: -0.0001

Data Index: 101179 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.7858. Min Act: -0.0001

Data Index: 631483 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.5432. Min Act: -0.0001

Data Index: 161127 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.2456. Min Act: -0.0001

Data Index: 691415 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.1689. Min Act: -0.0001

Data Index: 396298 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.6141. Min Act: -0.0001

Data Index: 1316201 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.4492. Min Act: -0.0001

Data Index: 1359421 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.4456. Min Act: -0.0001

Data Index: 528591 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.1429. Min Act: -0.0001

Data Index: 131309 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.3994. Min Act: -0.0001

Data Index: 375677 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.3849. Min Act: -0.0001

Data Index: 1104567 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.0568. Min Act: -0.0001

Data Index: 574087 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.7858. Min Range: -3.7858

Max Act: 2.9700. Min Act: -0.0001

Data Index: 6555 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.3612. Min Act: -0.0001

Data Index: 751683 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.6578. Min Act: -0.0001

Data Index: 430421 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.0764. Min Act: -0.0001

Data Index: 1355470 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.1528. Min Act: -0.0001

Data Index: 612971 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.7858. Min Range: -3.7858

Max Act: 2.9940. Min Act: -0.0001

Data Index: 331456 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 3.7858. Min Range: -3.7858

Max Act: 3.1213. Min Act: -0.0001

Data Index: 770879 (C4 (Web Text))

Max Activating Token Index: 431