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

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

Neuron 3730 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1022588 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3548. Min Act: -0.0000

Data Index: 328719 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3070. Min Act: -0.0000

Data Index: 299024 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3175. Min Act: -0.0000

Data Index: 12634 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1091275 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3339. Min Act: -0.0000

Data Index: 14606 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3116. Min Act: -0.0000

Data Index: 677952 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2832. Min Act: -0.0000

Data Index: 582775 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2867. Min Act: -0.0000

Data Index: 369278 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2776. Min Act: -0.0000

Data Index: 758436 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2600. Min Act: -0.0000

Data Index: 681605 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2967. Min Act: -0.0000

Data Index: 266906 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2738. Min Act: -0.0000

Data Index: 546888 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3135. Min Act: -0.0000

Data Index: 903234 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2873. Min Act: -0.0000

Data Index: 352601 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2630. Min Act: -0.0000

Data Index: 814551 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2904. Min Act: -0.0000

Data Index: 297717 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2788. Min Act: -0.0000

Data Index: 403445 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2634. Min Act: -0.0000

Data Index: 545319 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2150. Min Act: -0.0000

Data Index: 525662 (C4 (Web Text))

Max Activating Token Index: 312