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

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

Neuron 3175 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.4849. Min Act: -0.0000

Data Index: 419360 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.5311. Min Act: -0.0000

Data Index: 572985 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.1608. Min Act: -0.0000

Data Index: 130368 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.1843. Min Act: -0.0000

Data Index: 703629 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.0938. Min Act: -0.0000

Data Index: 402913 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 2.5311. Min Range: -2.5311

Max Act: 2.1748. Min Act: -0.0000

Data Index: 604556 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.9785. Min Act: -0.0000

Data Index: 98766 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.8946. Min Act: -0.0000

Data Index: 381655 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.8533. Min Act: -0.0000

Data Index: 595483 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.7179. Min Act: -0.0000

Data Index: 772550 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.7823. Min Act: -0.0000

Data Index: 1340168 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.8409. Min Act: -0.0000

Data Index: 1020229 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.7519. Min Act: -0.0000

Data Index: 49575 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1074348 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.5381. Min Act: -0.0000

Data Index: 158082 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.5975. Min Act: -0.0000

Data Index: 1036845 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.5157. Min Act: -0.0000

Data Index: 338183 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.4321. Min Act: -0.0000

Data Index: 99008 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.6546. Min Act: -0.0000

Data Index: 520516 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.5311. Min Range: -2.5311

Max Act: 1.5375. Min Act: -0.0000

Data Index: 231474 (C4 (Web Text))

Max Activating Token Index: 728