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

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

Neuron 538 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: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0000

Data Index: 830067 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0645. Min Act: -0.0000

Data Index: 225423 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0635. Min Act: -0.0000

Data Index: 940290 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0597. Min Act: -0.0000

Data Index: 453750 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0560. Min Act: -0.0000

Data Index: 325133 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1313992 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1163551 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0538. Min Act: -0.0000

Data Index: 969359 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0544. Min Act: -0.0000

Data Index: 332480 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0503. Min Act: -0.0000

Data Index: 506582 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1170424 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0552. Min Act: -0.0001

Data Index: 794471 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0518. Min Act: -0.0001

Data Index: 749691 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0496. Min Act: -0.0001

Data Index: 62423 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0504. Min Act: -0.0000

Data Index: 726142 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0514. Min Act: -0.0001

Data Index: 284942 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1317120 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1068050 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0488. Min Act: -0.0000

Data Index: 110563 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1010552 (C4 (Web Text))

Max Activating Token Index: 403