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

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

Neuron 2756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5379. Min Act: -0.0000

Data Index: 387730 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5529. Min Act: -0.0000

Data Index: 68067 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.5191. Min Act: -0.0000

Data Index: 21892 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4256. Min Act: -0.0000

Data Index: 590849 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4494. Min Act: -0.0000

Data Index: 978423 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4515. Min Act: -0.0000

Data Index: 530795 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4392. Min Act: -0.0000

Data Index: 267057 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4827. Min Act: -0.0000

Data Index: 357168 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4285. Min Act: -0.0000

Data Index: 386873 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3846. Min Act: -0.0000

Data Index: 411485 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3749. Min Act: -0.0000

Data Index: 285106 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4430. Min Act: -0.0000

Data Index: 639743 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3523. Min Act: -0.0000

Data Index: 825297 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3972. Min Act: -0.0000

Data Index: 796362 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.4373. Min Act: -0.0000

Data Index: 723449 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3793. Min Act: -0.0000

Data Index: 197443 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3832. Min Act: -0.0000

Data Index: 887634 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1133365 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3743. Min Act: -0.0000

Data Index: 884162 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.5529. Min Range: -1.5529

Max Act: 1.3624. Min Act: -0.0000

Data Index: 490748 (C4 (Web Text))

Max Activating Token Index: 316