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

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

Neuron 3242 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0495. Min Range: -2.0495

Max Act: 2.0459. Min Act: -0.0000

Data Index: 884977 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.0495. Min Range: -2.0495

Max Act: 2.0495. Min Act: -0.0000

Data Index: 1280573 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.7009. Min Act: -0.0000

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 2.0495. Min Range: -2.0495

Max Act: 2.0084. Min Act: -0.0000

Data Index: 940341 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.7179. Min Act: -0.0000

Data Index: 552008 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.6457. Min Act: -0.0000

Data Index: 959046 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.7356. Min Act: -0.0000

Data Index: 598658 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.7250. Min Act: -0.0000

Data Index: 571056 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.6082. Min Act: -0.0000

Data Index: 78175 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.4957. Min Act: -0.0000

Data Index: 449919 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.4878. Min Act: -0.0000

Data Index: 408365 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.5645. Min Act: -0.0000

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.5651. Min Act: -0.0000

Data Index: 85763 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.5883. Min Act: -0.0000

Data Index: 77896 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.4910. Min Act: -0.0000

Data Index: 616688 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.6501. Min Act: -0.0000

Data Index: 760846 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1359409 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.5519. Min Act: -0.0000

Data Index: 743308 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 2.0495. Min Range: -2.0495

Max Act: 1.4402. Min Act: -0.0000

Data Index: 331434 (C4 (Web Text))

Max Activating Token Index: 719