Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1682 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1045389 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0126. Min Act: -0.0003

Data Index: 640386 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0124. Min Act: -0.0003

Data Index: 551601 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0124. Min Act: -0.0003

Data Index: 934843 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1061415 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0123. Min Act: -0.0003

Data Index: 590725 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0121. Min Act: -0.0003

Data Index: 901822 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0122. Min Act: -0.0003

Data Index: 928453 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0122. Min Act: -0.0003

Data Index: 536969 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0121. Min Act: -0.0003

Data Index: 479887 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0121. Min Act: -0.0003

Data Index: 857783 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0003

Data Index: 986232 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0121. Min Act: -0.0003

Data Index: 857284 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0118. Min Act: -0.0003

Data Index: 246516 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0003

Data Index: 120971 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0118. Min Act: -0.0003

Data Index: 632912 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0003

Data Index: 436260 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0003

Data Index: 204308 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1180722 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0118. Min Act: -0.0003

Data Index: 701673 (C4 (Web Text))

Max Activating Token Index: 674