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

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

Neuron 2283 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: 2.0128. Min Range: -2.0128

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1003718 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.9358. Min Act: 0.0000

Data Index: 833833 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.9614. Min Act: -0.0000

Data Index: 745305 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.8551. Min Act: -0.0000

Data Index: 409489 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.8270. Min Act: 0.0001

Data Index: 436138 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1321555 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1136415 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.7199. Min Act: 0.0001

Data Index: 851035 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.7012. Min Act: -0.0000

Data Index: 528115 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1019984 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1359330 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.6031. Min Act: -0.0000

Data Index: 519732 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4959. Min Act: -0.0000

Data Index: 782350 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4971. Min Act: -0.0000

Data Index: 231903 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4791. Min Act: -0.0000

Data Index: 827444 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4705. Min Act: -0.0000

Data Index: 226042 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4731. Min Act: 0.0000

Data Index: 1233037 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4602. Min Act: -0.0000

Data Index: 502754 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4696. Min Act: -0.0000

Data Index: 92887 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 2.0128. Min Range: -2.0128

Max Act: 1.4467. Min Act: -0.0000

Data Index: 247478 (C4 (Web Text))

Max Activating Token Index: 195