Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0775. Min Act: -0.0000

Data Index: 62918 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0666. Min Act: -0.0000

Data Index: 52772 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1284269 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0136. Min Act: -0.0000

Data Index: 28288 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0161. Min Act: -0.0000

Data Index: 680317 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1336201 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0109. Min Act: -0.0000

Data Index: 51263 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9472. Min Act: -0.0000

Data Index: 626009 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8593. Min Act: -0.0000

Data Index: 201690 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9279. Min Act: -0.0000

Data Index: 989778 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1320905 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9820. Min Act: -0.0000

Data Index: 321143 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9587. Min Act: -0.0000

Data Index: 15163 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1162709 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8678. Min Act: -0.0000

Data Index: 700119 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9071. Min Act: -0.0000

Data Index: 979186 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8770. Min Act: -0.0000

Data Index: 82685 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9303. Min Act: -0.0000

Data Index: 939276 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8760. Min Act: -0.0000

Data Index: 103924 (C4 (Web Text))

Max Activating Token Index: 635