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

Dataset: The Pile

Neuron 362 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: 1.6377. Min Range: -1.6377

Max Act: 1.5484. Min Act: -0.0000

Data Index: 813924 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.6377. Min Act: -0.0000

Data Index: 882495 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1016447 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1930622 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1255944 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0650. Min Act: -0.0000

Data Index: 882686 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1570228 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1258651 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0638. Min Act: -0.0000

Data Index: 895508 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9090. Min Act: -0.0000

Data Index: 454142 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8458. Min Act: -0.0000

Data Index: 889310 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1773644 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1666950 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1826190 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8138. Min Act: -0.0000

Data Index: 688838 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1014994 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9467. Min Act: -0.0000

Data Index: 61486 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1559957 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.7882. Min Act: -0.0000

Data Index: 836510 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8103. Min Act: -0.0000

Data Index: 744933 (The Pile)

Max Activating Token Index: 140