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

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

Neuron 2589 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5809. Min Act: -0.0002

Data Index: 113043 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5175. Min Act: -0.0002

Data Index: 867541 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5086. Min Act: -0.0002

Data Index: 1337752 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5496. Min Act: -0.0001

Data Index: 596184 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4809. Min Act: -0.0001

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5091. Min Act: -0.0002

Data Index: 945003 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4942. Min Act: -0.0001

Data Index: 189506 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4547. Min Act: -0.0002

Data Index: 1223485 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4561. Min Act: -0.0002

Data Index: 524807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4880. Min Act: -0.0001

Data Index: 378130 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4526. Min Act: -0.0001

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4858. Min Act: -0.0002

Data Index: 984318 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4617. Min Act: -0.0002

Data Index: 1198180 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4957. Min Act: -0.0001

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5059. Min Act: -0.0001

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4598. Min Act: -0.0002

Data Index: 921901 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4532. Min Act: -0.0002

Data Index: 1078441 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4389. Min Act: -0.0002

Data Index: 9039 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4586. Min Act: -0.0001

Data Index: 419312 (C4 (Web Text))

Max Activating Token Index: 96