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

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

Neuron 78 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4608. Min Act: -0.0001

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.5316. Min Act: -0.0001

Data Index: 455310 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4507. Min Act: -0.0001

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4647. Min Act: -0.0001

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4246. Min Act: -0.0001

Data Index: 149515 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4826. Min Act: -0.0001

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4335. Min Act: -0.0001

Data Index: 1163529 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4279. Min Act: -0.0001

Data Index: 572794 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3911. Min Act: -0.0001

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3958. Min Act: -0.0001

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3874. Min Act: -0.0001

Data Index: 584193 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4190. Min Act: -0.0001

Data Index: 17985 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4026. Min Act: -0.0001

Data Index: 605575 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3994. Min Act: -0.0001

Data Index: 509393 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4133. Min Act: -0.0001

Data Index: 287014 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3931. Min Act: -0.0001

Data Index: 319657 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3436. Min Act: -0.0001

Data Index: 1249852 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3821. Min Act: -0.0001

Data Index: 169201 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3795. Min Act: -0.0001

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3110. Min Act: -0.0001

Data Index: 947109 (C4 (Web Text))

Max Activating Token Index: 266