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

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

Neuron 3659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.1051. Min Act: -0.0000

Data Index: 689322 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.1182. Min Act: -0.0000

Data Index: 1309785 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.5005. Min Act: -0.0000

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.3191. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.0805. Min Act: -0.0000

Data Index: 709038 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 2.5005. Min Range: -2.5005

Max Act: 2.0417. Min Act: -0.0000

Data Index: 512525 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.8271. Min Act: -0.0000

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.9161. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.2693. Min Act: -0.0000

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1355257 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.3431. Min Act: -0.0000

Data Index: 670174 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.3139. Min Act: -0.0000

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.1153. Min Act: -0.0000

Data Index: 678250 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1021205 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.2092. Min Act: -0.0000

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.1987. Min Act: -0.0000

Data Index: 816387 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.1471. Min Act: -0.0000

Data Index: 780962 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 2.5005. Min Range: -2.5005

Max Act: 1.0776. Min Act: -0.0000

Data Index: 898105 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 2.5005. Min Range: -2.5005

Max Act: 0.9983. Min Act: -0.0000

Data Index: 216427 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 2.5005. Min Range: -2.5005

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1276005 (C4 (Web Text))

Max Activating Token Index: 134