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

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

Neuron 496 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: 5.8126. Min Range: -5.8126

Max Act: 5.6594. Min Act: -0.0001

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.5967. Min Act: -0.0001

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.8126. Min Act: -0.0001

Data Index: 86220 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.5186. Min Act: -0.0001

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4806. Min Act: -0.0001

Data Index: 69804 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4382. Min Act: -0.0001

Data Index: 217095 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3480. Min Act: -0.0001

Data Index: 977644 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.5069. Min Act: -0.0001

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.5037. Min Act: -0.0001

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3071. Min Act: -0.0001

Data Index: 793863 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.1406. Min Act: -0.0001

Data Index: 824721 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3059. Min Act: -0.0001

Data Index: 1044865 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.1287. Min Act: -0.0001

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.1185. Min Act: -0.0001

Data Index: 624064 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.2794. Min Act: -0.0001

Data Index: 574842 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.2720. Min Act: -0.0001

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4412. Min Act: -0.0001

Data Index: 818437 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4437. Min Act: -0.0001

Data Index: 127085 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.0753. Min Act: -0.0001

Data Index: 367770 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3717. Min Act: -0.0001

Data Index: 860648 (C4 (Web Text))

Max Activating Token Index: 499