Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1660 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7967. Min Act: -0.0000

Data Index: 450584 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5996. Min Act: -0.0000

Data Index: 924720 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6112. Min Act: -0.0000

Data Index: 25080 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5348. Min Act: -0.0000

Data Index: 52701 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5410. Min Act: -0.0000

Data Index: 194461 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1194545 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4905. Min Act: -0.0000

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5082. Min Act: -0.0000

Data Index: 293061 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5032. Min Act: -0.0000

Data Index: 630377 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4892. Min Act: -0.0000

Data Index: 99765 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.5023. Min Act: -0.0000

Data Index: 571127 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1057980 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4931. Min Act: -0.0000

Data Index: 997375 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4744. Min Act: -0.0000

Data Index: 296908 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4292. Min Act: -0.0000

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4557. Min Act: -0.0000

Data Index: 506928 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1111461 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1154396 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.4101. Min Act: -0.0000

Data Index: 994646 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 700