Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.6403. Min Act: -0.0001

Data Index: 1282558 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5745. Min Act: -0.0001

Data Index: 181520 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5622. Min Act: -0.0001

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5519. Min Act: -0.0001

Data Index: 911320 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1400913 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5956. Min Act: -0.0001

Data Index: 337626 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5319. Min Act: -0.0001

Data Index: 425233 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5848. Min Act: -0.0001

Data Index: 106027 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1431660 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5514. Min Act: -0.0001

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5828. Min Act: -0.0001

Data Index: 477395 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5046. Min Act: -0.0001

Data Index: 109915 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5546. Min Act: -0.0001

Data Index: 874296 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5504. Min Act: -0.0001

Data Index: 674881 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5066. Min Act: -0.0001

Data Index: 371082 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1281888 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4703. Min Act: -0.0001

Data Index: 872353 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4958. Min Act: -0.0001

Data Index: 1569796 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.5105. Min Act: -0.0001

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.6403. Min Range: -0.6403

Max Act: 0.4940. Min Act: -0.0001

Data Index: 1146894 (C4 (Web Text))

Max Activating Token Index: 202