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

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

Neuron 4934 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1655727 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5503. Min Act: -0.0000

Data Index: 677663 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5338. Min Act: -0.0000

Data Index: 238955 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1130492 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1145230 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4224. Min Act: -0.0000

Data Index: 311686 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4623. Min Act: -0.0000

Data Index: 91519 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4153. Min Act: -0.0000

Data Index: 615390 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4278. Min Act: -0.0000

Data Index: 402055 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4254. Min Act: -0.0000

Data Index: 707268 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3955. Min Act: -0.0000

Data Index: 772185 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4352. Min Act: -0.0000

Data Index: 977787 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4110. Min Act: -0.0000

Data Index: 157806 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4091. Min Act: -0.0000

Data Index: 779015 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.4023. Min Act: -0.0000

Data Index: 41647 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3701. Min Act: -0.0000

Data Index: 265279 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3526. Min Act: -0.0000

Data Index: 334385 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3701. Min Act: -0.0000

Data Index: 567910 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.5943. Min Range: -0.5943

Max Act: 0.3668. Min Act: -0.0000

Data Index: 453292 (C4 (Web Text))

Max Activating Token Index: 879