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

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

Neuron 4103 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: 2.4568. Min Range: -2.4568

Max Act: 2.4568. Min Act: -0.0000

Data Index: 402286 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.4568. Min Range: -2.4568

Max Act: 2.3974. Min Act: -0.0000

Data Index: 967799 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.9980. Min Act: -0.0000

Data Index: 231176 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.8462. Min Act: -0.0000

Data Index: 251039 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.5760. Min Act: -0.0000

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.4677. Min Act: -0.0000

Data Index: 537325 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.5060. Min Act: -0.0000

Data Index: 46363 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.5421. Min Act: -0.0000

Data Index: 154731 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.2685. Min Act: -0.0000

Data Index: 803686 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.4179. Min Act: -0.0000

Data Index: 948715 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1010786 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.3937. Min Act: -0.0000

Data Index: 305258 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1231481 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.4289. Min Act: -0.0000

Data Index: 865412 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.4125. Min Act: -0.0000

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.3136. Min Act: -0.0000

Data Index: 1243782 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1074328 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.2814. Min Act: -0.0000

Data Index: 153558 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.1551. Min Act: -0.0000

Data Index: 246022 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 2.4568. Min Range: -2.4568

Max Act: 1.2764. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 620