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

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

Neuron 2536 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.9392. Min Act: -0.0000

Data Index: 271347 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.8330. Min Act: -0.0000

Data Index: 762544 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1251051 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6731. Min Act: -0.0000

Data Index: 53313 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6483. Min Act: -0.0000

Data Index: 485459 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1148137 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6539. Min Act: -0.0000

Data Index: 322506 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.6402. Min Act: 0.0000

Data Index: 834642 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5916. Min Act: -0.0000

Data Index: 65402 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1060786 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5843. Min Act: -0.0000

Data Index: 326151 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5757. Min Act: -0.0000

Data Index: 948012 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5894. Min Act: -0.0000

Data Index: 789935 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1134214 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5627. Min Act: -0.0000

Data Index: 112341 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5760. Min Act: -0.0000

Data Index: 325289 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5588. Min Act: -0.0000

Data Index: 137064 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5227. Min Act: -0.0000

Data Index: 408183 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5369. Min Act: -0.0000

Data Index: 272257 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.9392. Min Range: -0.9392

Max Act: 0.5219. Min Act: -0.0000

Data Index: 822761 (C4 (Web Text))

Max Activating Token Index: 274