Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1436 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.5522. Min Act: -0.0002

Data Index: 715127 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.5330. Min Act: -0.0001

Data Index: 461182 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4817. Min Act: -0.0002

Data Index: 148864 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4857. Min Act: -0.0002

Data Index: 735302 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4318. Min Act: -0.0002

Data Index: 885183 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4833. Min Act: -0.0001

Data Index: 877177 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1342378 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4794. Min Act: -0.0001

Data Index: 1649839 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4544. Min Act: -0.0001

Data Index: 916493 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4678. Min Act: -0.0001

Data Index: 11848 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1293295 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4648. Min Act: -0.0001

Data Index: 464853 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4972. Min Act: -0.0002

Data Index: 779179 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4666. Min Act: -0.0001

Data Index: 469000 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4478. Min Act: -0.0001

Data Index: 28021 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4886. Min Act: -0.0002

Data Index: 1029039 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.5028. Min Act: -0.0002

Data Index: 203036 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4555. Min Act: -0.0002

Data Index: 1335347 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4434. Min Act: -0.0002

Data Index: 296924 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.5522. Min Range: -0.5522

Max Act: 0.4390. Min Act: -0.0001

Data Index: 701833 (C4 (Web Text))

Max Activating Token Index: 794