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

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

Neuron 1432 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0224. Min Range: -1.0224

Max Act: 1.0094. Min Act: -0.0000

Data Index: 48060 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.0224. Min Range: -1.0224

Max Act: 1.0224. Min Act: -0.0000

Data Index: 554040 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.6614. Min Act: -0.0000

Data Index: 616926 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1422912 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1323366 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4516. Min Act: -0.0000

Data Index: 439846 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5353. Min Act: -0.0000

Data Index: 619296 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1513678 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1400116 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5430. Min Act: -0.0000

Data Index: 556083 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1566022 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1040837 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1571183 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1563619 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5967. Min Act: -0.0000

Data Index: 78313 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4603. Min Act: -0.0000

Data Index: 423495 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5031. Min Act: -0.0000

Data Index: 73270 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4838. Min Act: -0.0000

Data Index: 901134 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1434762 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1220335 (C4 (Web Text))

Max Activating Token Index: 172