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

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

Neuron 3453 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0918. Min Range: -3.0918

Max Act: 3.0918. Min Act: -0.0000

Data Index: 293209 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.8685. Min Act: -0.0000

Data Index: 446342 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.6469. Min Act: -0.0000

Data Index: 334320 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.5914. Min Act: -0.0000

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.7334. Min Act: -0.0000

Data Index: 341734 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.8868. Min Act: -0.0000

Data Index: 912627 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.5583. Min Act: -0.0000

Data Index: 541226 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.6434. Min Act: -0.0000

Data Index: 716404 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.3436. Min Act: -0.0000

Data Index: 1345260 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.3293. Min Act: -0.0000

Data Index: 7357 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.1592. Min Act: -0.0000

Data Index: 520346 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.5292. Min Act: -0.0000

Data Index: 1046450 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.3716. Min Act: -0.0000

Data Index: 1160656 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.4382. Min Act: -0.0000

Data Index: 624344 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.1854. Min Act: -0.0000

Data Index: 1497057 (Python Code)

Max Activating Token Index: 692

Text #15

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.2882. Min Act: -0.0000

Data Index: 49051 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1298913 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.3674. Min Act: -0.0000

Data Index: 1499521 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.1294. Min Act: -0.0000

Data Index: 769216 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 3.0918. Min Range: -3.0918

Max Act: 2.1181. Min Act: -0.0000

Data Index: 576938 (C4 (Web Text))

Max Activating Token Index: 558