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

Dataset: The Pile

Neuron 995 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: 4.9639. Min Range: -4.9639

Max Act: 4.8788. Min Act: -0.0000

Data Index: 1090090 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 4.9639. Min Range: -4.9639

Max Act: 4.9639. Min Act: -0.0000

Data Index: 1768735 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.8913. Min Act: -0.0000

Data Index: 1355400 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 4.9639. Min Range: -4.9639

Max Act: 4.0169. Min Act: -0.0000

Data Index: 895283 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6738. Min Act: -0.0000

Data Index: 358205 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.7817. Min Act: -0.0000

Data Index: 1328952 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.8924. Min Act: -0.0000

Data Index: 1504928 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.7394. Min Act: -0.0000

Data Index: 1612560 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.7206. Min Act: -0.0000

Data Index: 1119289 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6818. Min Act: -0.0000

Data Index: 46203 (The Pile)

Max Activating Token Index: 712

Text #10

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.8127. Min Act: -0.0000

Data Index: 86853 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.8236. Min Act: -0.0000

Data Index: 934836 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6355. Min Act: -0.0000

Data Index: 1918092 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6176. Min Act: -0.0000

Data Index: 1769339 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.7031. Min Act: -0.0000

Data Index: 498038 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.3893. Min Act: -0.0000

Data Index: 1006528 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6839. Min Act: -0.0000

Data Index: 787545 (The Pile)

Max Activating Token Index: 915

Text #17

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.5184. Min Act: -0.0000

Data Index: 1420888 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.8107. Min Act: -0.0000

Data Index: 705006 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 4.9639. Min Range: -4.9639

Max Act: 3.6474. Min Act: -0.0000

Data Index: 1715514 (The Pile)

Max Activating Token Index: 952