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

Dataset: The Pile

Neuron 3990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.4531. Min Act: -0.0000

Data Index: 845883 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9454. Min Act: -0.0000

Data Index: 922445 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1074959 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9684. Min Act: -0.0000

Data Index: 862870 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9027. Min Act: -0.0000

Data Index: 268334 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0142. Min Act: -0.0000

Data Index: 330564 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1410806 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9166. Min Act: -0.0000

Data Index: 535845 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1907243 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7831. Min Act: -0.0000

Data Index: 131884 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1675283 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1996698 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1126995 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1370779 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1955962 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7662. Min Act: -0.0000

Data Index: 492507 (The Pile)

Max Activating Token Index: 985

Text #16

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7879. Min Act: -0.0000

Data Index: 69011 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1666662 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1105494 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8135. Min Act: -0.0000

Data Index: 119057 (The Pile)

Max Activating Token Index: 377