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

Dataset: The Pile

Neuron 1695 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.6421. Min Act: -0.0000

Data Index: 1872239 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.2156. Min Act: -0.0000

Data Index: 445145 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.9554. Min Act: -0.0000

Data Index: 1308560 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.1895. Min Act: -0.0000

Data Index: 1575998 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.0009. Min Act: -0.0000

Data Index: 1180694 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.7658. Min Act: -0.0000

Data Index: 1944053 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.9689. Min Act: -0.0000

Data Index: 1786448 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8347. Min Act: -0.0000

Data Index: 1321679 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8891. Min Act: -0.0000

Data Index: 1294542 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8710. Min Act: -0.0000

Data Index: 883835 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.7244. Min Act: -0.0000

Data Index: 1931297 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.6988. Min Act: -0.0000

Data Index: 1935281 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.4363. Min Act: -0.0000

Data Index: 1171951 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1085409 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1704374 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.5148. Min Act: -0.0000

Data Index: 1288985 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.6336. Min Act: -0.0000

Data Index: 916931 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.6051. Min Act: -0.0000

Data Index: 207525 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.4889. Min Act: -0.0000

Data Index: 1718849 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.4556. Min Act: -0.0000

Data Index: 1645843 (The Pile)

Max Activating Token Index: 517