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

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

Neuron 3811 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8048. Min Range: -7.8048

Max Act: 7.8048. Min Act: -0.0000

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 7.8048. Min Range: -7.8048

Max Act: 6.8940. Min Act: -0.0000

Data Index: 882496 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.4703. Min Act: -0.0000

Data Index: 138153 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.6041. Min Act: -0.0000

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.5342. Min Act: -0.0000

Data Index: 1346062 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.2661. Min Act: -0.0000

Data Index: 1333000 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.2892. Min Act: -0.0000

Data Index: 1064400 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.8894. Min Act: -0.0000

Data Index: 804503 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.2701. Min Act: -0.0000

Data Index: 544065 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.0691. Min Act: -0.0000

Data Index: 961498 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.2051. Min Act: -0.0000

Data Index: 983670 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.9496. Min Act: -0.0000

Data Index: 181519 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.7221. Min Act: -0.0000

Data Index: 527753 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.1008. Min Act: -0.0000

Data Index: 456833 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.0736. Min Act: -0.0000

Data Index: 821791 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.6576. Min Act: -0.0000

Data Index: 423534 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.8737. Min Act: -0.0000

Data Index: 1112307 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.8515. Min Act: -0.0000

Data Index: 712000 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 7.8048. Min Range: -7.8048

Max Act: 5.0177. Min Act: -0.0000

Data Index: 661445 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 7.8048. Min Range: -7.8048

Max Act: 4.9678. Min Act: -0.0000

Data Index: 166403 (C4 (Web Text))

Max Activating Token Index: 896