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

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

Neuron 1471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6909. Min Act: -0.0001

Data Index: 191337 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6126. Min Act: -0.0000

Data Index: 74581 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.6086. Min Act: -0.0000

Data Index: 450407 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5680. Min Act: -0.0000

Data Index: 6637 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5391. Min Act: -0.0001

Data Index: 579048 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5669. Min Act: -0.0000

Data Index: 74340 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5263. Min Act: -0.0001

Data Index: 808593 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5420. Min Act: -0.0000

Data Index: 27851 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5356. Min Act: -0.0000

Data Index: 498435 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1242930 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4827. Min Act: -0.0000

Data Index: 415868 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.5292. Min Act: -0.0000

Data Index: 622631 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1335116 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4471. Min Act: -0.0000

Data Index: 58487 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1159397 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1255544 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1284321 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4499. Min Act: -0.0000

Data Index: 725699 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4452. Min Act: -0.0001

Data Index: 11551 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.6909. Min Range: -0.6909

Max Act: 0.4481. Min Act: -0.0000

Data Index: 176617 (C4 (Web Text))

Max Activating Token Index: 631