Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0000

Data Index: 179179 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1323812 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6018. Min Act: -0.0000

Data Index: 544748 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5884. Min Act: -0.0001

Data Index: 599073 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5657. Min Act: -0.0001

Data Index: 669591 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5826. Min Act: 0.0000

Data Index: 627302 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5627. Min Act: -0.0000

Data Index: 603904 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5416. Min Act: -0.0000

Data Index: 140801 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5680. Min Act: -0.0000

Data Index: 814287 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5842. Min Act: -0.0000

Data Index: 863181 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5285. Min Act: -0.0000

Data Index: 459049 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5137. Min Act: -0.0000

Data Index: 239891 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1098668 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4819. Min Act: -0.0000

Data Index: 607002 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5041. Min Act: -0.0000

Data Index: 952885 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1002122 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4892. Min Act: 0.0000

Data Index: 353481 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4864. Min Act: -0.0000

Data Index: 370518 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4700. Min Act: -0.0000

Data Index: 686091 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4586. Min Act: 0.0000

Data Index: 324436 (C4 (Web Text))

Max Activating Token Index: 380