Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1456795 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.2069. Min Act: -0.0000

Data Index: 609229 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1294813 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1509363 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0863. Min Act: -0.0000

Data Index: 450715 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9783. Min Act: -0.0000

Data Index: 324500 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1576355 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1327759 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9162. Min Act: -0.0000

Data Index: 52467 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1898941 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1647770 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9539. Min Act: -0.0000

Data Index: 890862 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1283834 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8602. Min Act: -0.0000

Data Index: 382335 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9109. Min Act: -0.0000

Data Index: 967508 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9078. Min Act: -0.0000

Data Index: 328930 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9724. Min Act: -0.0000

Data Index: 120316 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1048206 (The Pile)

Max Activating Token Index: 732

Text #18

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8975. Min Act: -0.0000

Data Index: 26136 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1646820 (The Pile)

Max Activating Token Index: 772