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

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

Neuron 3056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4535. Min Act: -0.0002

Data Index: 1226957 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4437. Min Act: -0.0002

Data Index: 1074316 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4433. Min Act: -0.0002

Data Index: 408052 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4368. Min Act: -0.0002

Data Index: 199130 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4181. Min Act: -0.0002

Data Index: 100366 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4066. Min Act: -0.0002

Data Index: 762727 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4043. Min Act: -0.0002

Data Index: 1069157 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4022. Min Act: -0.0002

Data Index: 373241 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.4016. Min Act: -0.0002

Data Index: 271280 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3786. Min Act: -0.0002

Data Index: 12471 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3985. Min Act: -0.0002

Data Index: 1122823 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3964. Min Act: -0.0002

Data Index: 254374 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3960. Min Act: -0.0002

Data Index: 443181 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3962. Min Act: -0.0002

Data Index: 691174 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3943. Min Act: -0.0002

Data Index: 70265 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3920. Min Act: -0.0002

Data Index: 1343798 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3900. Min Act: -0.0002

Data Index: 1267001 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3904. Min Act: -0.0002

Data Index: 470088 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3985. Min Act: -0.0002

Data Index: 1345150 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.4535. Min Range: -0.4535

Max Act: 0.3832. Min Act: -0.0002

Data Index: 1211076 (C4 (Web Text))

Max Activating Token Index: 728