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

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

Neuron 3401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6924. Min Act: 0.0000

Data Index: 1064513 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1127291 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6628. Min Act: 0.0001

Data Index: 773299 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6572. Min Act: -0.0000

Data Index: 165072 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1283070 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6395. Min Act: 0.0000

Data Index: 1109226 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1116783 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1125638 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1307582 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6156. Min Act: -0.0000

Data Index: 50710 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5740. Min Act: -0.0001

Data Index: 582225 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6180. Min Act: 0.0001

Data Index: 1153931 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5965. Min Act: -0.0001

Data Index: 598005 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5927. Min Act: -0.0000

Data Index: 542347 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5673. Min Act: -0.0000

Data Index: 933565 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5511. Min Act: -0.0000

Data Index: 96933 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5594. Min Act: -0.0000

Data Index: 781813 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5811. Min Act: -0.0000

Data Index: 895132 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5439. Min Act: -0.0001

Data Index: 183093 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5708. Min Act: 0.0001

Data Index: 1026993 (C4 (Web Text))

Max Activating Token Index: 297