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

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

Neuron 76 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: 3.5616. Min Range: -3.5616

Max Act: 3.5616. Min Act: -0.0001

Data Index: 1153599 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 3.5616. Min Range: -3.5616

Max Act: 3.3472. Min Act: -0.0002

Data Index: 57601 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.7913. Min Act: -0.0001

Data Index: 254043 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.4841. Min Act: -0.0002

Data Index: 912894 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.3597. Min Act: -0.0001

Data Index: 377250 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.5776. Min Act: -0.0001

Data Index: 172891 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.2046. Min Act: -0.0002

Data Index: 1017143 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.2970. Min Act: -0.0001

Data Index: 1226039 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.2394. Min Act: -0.0002

Data Index: 1154445 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 3.5616. Min Range: -3.5616

Max Act: 1.9601. Min Act: -0.0002

Data Index: 1191800 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.2425. Min Act: -0.0001

Data Index: 423675 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.1225. Min Act: -0.0001

Data Index: 686132 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.3580. Min Act: -0.0002

Data Index: 740545 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 3.5616. Min Range: -3.5616

Max Act: 1.9929. Min Act: -0.0002

Data Index: 184941 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.5616. Min Range: -3.5616

Max Act: 1.9821. Min Act: -0.0001

Data Index: 114872 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.0928. Min Act: -0.0001

Data Index: 274136 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.1681. Min Act: -0.0002

Data Index: 1089545 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.1530. Min Act: -0.0001

Data Index: 92134 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 3.5616. Min Range: -3.5616

Max Act: 1.9220. Min Act: -0.0001

Data Index: 750504 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.5616. Min Range: -3.5616

Max Act: 2.0112. Min Act: -0.0001

Data Index: 196767 (C4 (Web Text))

Max Activating Token Index: 233