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

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

Neuron 4706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.8652. Min Act: -0.0001

Data Index: 184601 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.6903. Min Act: -0.0001

Data Index: 114134 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1257120 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.7872. Min Act: -0.0000

Data Index: 899698 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1321219 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.7817. Min Act: -0.0001

Data Index: 59187 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.7727. Min Act: -0.0000

Data Index: 109229 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4814. Min Act: -0.0001

Data Index: 919698 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5230. Min Act: -0.0000

Data Index: 672086 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.3931. Min Act: -0.0000

Data Index: 652679 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5143. Min Act: -0.0001

Data Index: 491739 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1190384 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4150. Min Act: -0.0000

Data Index: 936455 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5998. Min Act: -0.0000

Data Index: 197698 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4498. Min Act: -0.0001

Data Index: 879776 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4841. Min Act: -0.0001

Data Index: 803761 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5246. Min Act: -0.0000

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.5613. Min Act: -0.0000

Data Index: 335239 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1077222 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.8652. Min Range: -1.8652

Max Act: 1.4713. Min Act: -0.0000

Data Index: 374547 (C4 (Web Text))

Max Activating Token Index: 182