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

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

Neuron 2304 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0710. Min Act: 0.0000

Data Index: 1327157 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1035579 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1146423 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1057284 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8114. Min Act: -0.0000

Data Index: 691425 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1010038 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7002. Min Act: 0.0000

Data Index: 179509 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6401. Min Act: -0.0000

Data Index: 723267 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1191328 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6356. Min Act: -0.0000

Data Index: 657928 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6456. Min Act: -0.0000

Data Index: 883589 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.6004. Min Act: 0.0000

Data Index: 122938 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.5731. Min Act: -0.0000

Data Index: 311477 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.5585. Min Act: 0.0000

Data Index: 713294 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1129242 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1206159 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.4972. Min Act: -0.0000

Data Index: 531984 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.4842. Min Act: -0.0000

Data Index: 248603 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1201712 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1316757 (C4 (Web Text))

Max Activating Token Index: 759