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

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

Neuron 4818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1080496 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6594. Min Act: -0.0000

Data Index: 723137 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5899. Min Act: -0.0001

Data Index: 162186 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1063521 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5982. Min Act: -0.0000

Data Index: 755874 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5570. Min Act: -0.0001

Data Index: 725164 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5713. Min Act: -0.0001

Data Index: 829886 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1150948 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5838. Min Act: -0.0001

Data Index: 135908 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5605. Min Act: -0.0001

Data Index: 354482 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5109. Min Act: -0.0001

Data Index: 871826 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1260756 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5671. Min Act: -0.0001

Data Index: 758583 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5534. Min Act: -0.0001

Data Index: 821050 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1054892 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5136. Min Act: -0.0001

Data Index: 267424 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4836. Min Act: -0.0001

Data Index: 422596 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5734. Min Act: -0.0001

Data Index: 127452 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1302083 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4719. Min Act: -0.0001

Data Index: 232152 (C4 (Web Text))

Max Activating Token Index: 165