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

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

Neuron 5292 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: 1.2288. Min Range: -1.2288

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1358652 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0899. Min Act: -0.0000

Data Index: 82254 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1177031 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1181073 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0298. Min Act: -0.0000

Data Index: 750591 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.2288. Min Range: -1.2288

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1533064 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1158057 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1117796 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8712. Min Act: -0.0000

Data Index: 992182 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1105465 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1645994 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8115. Min Act: -0.0000

Data Index: 838511 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8515. Min Act: -0.0000

Data Index: 963753 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1619612 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1232159 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1174051 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7615. Min Act: -0.0000

Data Index: 844328 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1379025 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.2288. Min Range: -1.2288

Max Act: 0.9081. Min Act: -0.0000

Data Index: 838267 (C4 (Web Text))

Max Activating Token Index: 879