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

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

Neuron 3171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: -0.0001

Data Index: 269662 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8689. Min Act: -0.0001

Data Index: 49800 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7955. Min Act: -0.0001

Data Index: 637723 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1008675 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1350773 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1303807 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7052. Min Act: -0.0001

Data Index: 1095787 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7376. Min Act: -0.0000

Data Index: 421748 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1299671 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6985. Min Act: -0.0000

Data Index: 810972 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6879. Min Act: -0.0001

Data Index: 293253 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6791. Min Act: -0.0001

Data Index: 1318030 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6651. Min Act: -0.0001

Data Index: 138825 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6609. Min Act: -0.0001

Data Index: 672841 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1184457 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6499. Min Act: -0.0000

Data Index: 131750 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6233. Min Act: -0.0000

Data Index: 478596 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6196. Min Act: -0.0000

Data Index: 907316 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6583. Min Act: -0.0000

Data Index: 597545 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6349. Min Act: -0.0001

Data Index: 306188 (C4 (Web Text))

Max Activating Token Index: 428