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

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

Neuron 2324 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: 6.9929. Min Range: -6.9929

Max Act: 6.9929. Min Act: -0.0000

Data Index: 1274941 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.8579. Min Act: -0.0000

Data Index: 596517 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 6.9929. Min Range: -6.9929

Max Act: 6.3057. Min Act: -0.0000

Data Index: 589171 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 6.9929. Min Range: -6.9929

Max Act: 6.1583. Min Act: -0.0000

Data Index: 1294491 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6686. Min Act: -0.0000

Data Index: 546613 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6650. Min Act: -0.0000

Data Index: 455350 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.4092. Min Act: -0.0000

Data Index: 775785 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.9299. Min Act: -0.0000

Data Index: 796778 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.8986. Min Act: -0.0000

Data Index: 590660 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.4591. Min Act: -0.0000

Data Index: 232595 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.2493. Min Act: -0.0000

Data Index: 947883 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6498. Min Act: -0.0000

Data Index: 1267945 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.8117. Min Act: -0.0000

Data Index: 673527 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6254. Min Act: -0.0000

Data Index: 357338 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6160. Min Act: -0.0000

Data Index: 216647 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.5530. Min Act: -0.0000

Data Index: 1051152 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.5106. Min Act: -0.0000

Data Index: 964217 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6976. Min Act: -0.0000

Data Index: 814164 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 6.9929. Min Range: -6.9929

Max Act: 6.3729. Min Act: -0.0000

Data Index: 735044 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 6.9929. Min Range: -6.9929

Max Act: 5.6594. Min Act: -0.0000

Data Index: 903820 (C4 (Web Text))

Max Activating Token Index: 902