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

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

Neuron 508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2980. Min Act: -0.0001

Data Index: 998424 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1559. Min Act: -0.0001

Data Index: 135674 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0762. Min Act: -0.0001

Data Index: 341670 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0119. Min Act: -0.0001

Data Index: 794690 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0873. Min Act: -0.0001

Data Index: 995289 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9882. Min Act: -0.0001

Data Index: 375588 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9782. Min Act: -0.0001

Data Index: 897580 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1231750 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.8688. Min Act: -0.0001

Data Index: 792264 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9694. Min Act: -0.0001

Data Index: 949116 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9722. Min Act: -0.0001

Data Index: 223941 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9129. Min Act: -0.0001

Data Index: 202456 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9370. Min Act: -0.0001

Data Index: 790552 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9277. Min Act: -0.0001

Data Index: 27113 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9027. Min Act: -0.0001

Data Index: 723563 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9671. Min Act: -0.0001

Data Index: 31523 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.8973. Min Act: -0.0001

Data Index: 747073 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0143. Min Act: -0.0001

Data Index: 592382 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9248. Min Act: -0.0001

Data Index: 63042 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9554. Min Act: -0.0001

Data Index: 640688 (C4 (Web Text))

Max Activating Token Index: 933