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

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

Neuron 459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 847310 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1159602 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0443. Min Act: -0.0002

Data Index: 294175 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0422. Min Act: -0.0002

Data Index: 173481 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0437. Min Act: -0.0002

Data Index: 754051 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0413. Min Act: -0.0002

Data Index: 813339 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1033206 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0428. Min Act: -0.0002

Data Index: 266580 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0427. Min Act: -0.0002

Data Index: 893756 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1234145 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0420. Min Act: -0.0002

Data Index: 265874 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0429. Min Act: -0.0002

Data Index: 137057 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1320654 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0399. Min Act: -0.0002

Data Index: 164336 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0441. Min Act: -0.0002

Data Index: 212981 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0376. Min Act: -0.0002

Data Index: 863269 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0415. Min Act: -0.0002

Data Index: 331464 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0394. Min Act: -0.0002

Data Index: 299813 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1220949 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1183541 (C4 (Web Text))

Max Activating Token Index: 519