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

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

Neuron 4260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.6475. Min Act: -0.0000

Data Index: 142721 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5006. Min Act: -0.0000

Data Index: 457273 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1503886 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1624727 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4538. Min Act: -0.0000

Data Index: 851239 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4460. Min Act: -0.0000

Data Index: 179429 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1421179 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1285178 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1516429 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1252115 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1448155 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4246. Min Act: -0.0000

Data Index: 830393 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1402765 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4461. Min Act: -0.0000

Data Index: 862964 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.3772. Min Act: -0.0000

Data Index: 571912 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4113. Min Act: -0.0000

Data Index: 264020 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.3658. Min Act: -0.0000

Data Index: 566278 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.3744. Min Act: -0.0000

Data Index: 67917 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1478827 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1513163 (Python Code)

Max Activating Token Index: 180