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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0832. Min Range: -4.0832

Max Act: 4.0175. Min Act: -0.0001

Data Index: 672508 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 4.0832. Min Range: -4.0832

Max Act: 4.0694. Min Act: -0.0001

Data Index: 267383 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 4.0832. Min Range: -4.0832

Max Act: 4.0489. Min Act: -0.0001

Data Index: 1035619 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 4.0832. Min Range: -4.0832

Max Act: 4.0832. Min Act: -0.0000

Data Index: 1296176 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.7014. Min Act: -0.0000

Data Index: 1203162 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.8866. Min Act: -0.0000

Data Index: 252547 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.7066. Min Act: -0.0000

Data Index: 99259 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6784. Min Act: -0.0000

Data Index: 963528 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.4480. Min Act: -0.0001

Data Index: 1277122 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5791. Min Act: -0.0000

Data Index: 663334 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.4475. Min Act: -0.0001

Data Index: 558044 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.3146. Min Act: -0.0001

Data Index: 865652 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5033. Min Act: -0.0001

Data Index: 212539 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.3660. Min Act: -0.0001

Data Index: 780806 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.3507. Min Act: -0.0001

Data Index: 1149531 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.4170. Min Act: -0.0000

Data Index: 1106729 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.4734. Min Act: -0.0000

Data Index: 1036109 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.3163. Min Act: -0.0000

Data Index: 396343 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5611. Min Act: -0.0001

Data Index: 87956 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.4691. Min Act: -0.0001

Data Index: 1025807 (C4 (Web Text))

Max Activating Token Index: 427