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

Dataset: The Pile

Neuron 4857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.7060. Min Act: -0.0000

Data Index: 949208 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1189005 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1551454 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1159935 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6883. Min Act: -0.0000

Data Index: 702679 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1654017 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1851127 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6435. Min Act: -0.0000

Data Index: 614367 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1994291 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6602. Min Act: -0.0000

Data Index: 175725 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1748452 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1293188 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1707369 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6593. Min Act: -0.0000

Data Index: 340625 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1174743 (The Pile)

Max Activating Token Index: 787

Text #15

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1024595 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1618360 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1191284 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6339. Min Act: -0.0000

Data Index: 321259 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 0.7504. Min Range: -0.7504

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1669381 (The Pile)

Max Activating Token Index: 24