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

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

Neuron 4996 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.1865. Min Act: -0.0001

Data Index: 7798 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.0172. Min Act: -0.0001

Data Index: 296976 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8027. Min Act: -0.0001

Data Index: 1043901 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8484. Min Act: -0.0001

Data Index: 1225118 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7195. Min Act: -0.0001

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.5287. Min Act: -0.0001

Data Index: 282732 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.3090. Min Act: -0.0001

Data Index: 374964 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.4311. Min Act: -0.0001

Data Index: 596861 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.3822. Min Act: -0.0001

Data Index: 371324 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.2823. Min Act: -0.0001

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.2670. Min Act: -0.0001

Data Index: 1209286 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.2955. Min Act: -0.0001

Data Index: 349390 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.1900. Min Act: -0.0001

Data Index: 752394 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.2840. Min Act: -0.0001

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.2913. Min Act: -0.0001

Data Index: 551581 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.4047. Min Act: -0.0001

Data Index: 237767 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.1617. Min Act: -0.0001

Data Index: 526487 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.1583. Min Act: -0.0001

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.3965. Min Act: -0.0001

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.1606. Min Act: -0.0001

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 785