Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2190 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.5649. Min Act: -0.0002

Data Index: 1143833 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4106. Min Act: -0.0002

Data Index: 216967 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.4258. Min Act: -0.0003

Data Index: 562713 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.2482. Min Act: -0.0002

Data Index: 924878 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.1528. Min Act: -0.0002

Data Index: 491447 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.2253. Min Act: -0.0002

Data Index: 172246 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.1310. Min Act: -0.0002

Data Index: 541866 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.0628. Min Act: -0.0002

Data Index: 81671 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 4.5649. Min Range: -4.5649

Max Act: 4.0502. Min Act: -0.0002

Data Index: 1177719 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.9937. Min Act: -0.0002

Data Index: 394491 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.8497. Min Act: -0.0002

Data Index: 355927 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.7665. Min Act: -0.0002

Data Index: 83061 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.7092. Min Act: -0.0002

Data Index: 1277871 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6876. Min Act: -0.0003

Data Index: 457575 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.7353. Min Act: -0.0002

Data Index: 249283 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6531. Min Act: -0.0002

Data Index: 1275697 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6974. Min Act: -0.0002

Data Index: 654155 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6830. Min Act: -0.0002

Data Index: 373928 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6976. Min Act: -0.0002

Data Index: 703946 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 4.5649. Min Range: -4.5649

Max Act: 3.6381. Min Act: -0.0002

Data Index: 779322 (C4 (Web Text))

Max Activating Token Index: 879