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

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

Neuron 3663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4973. Min Act: -0.0002

Data Index: 1262786 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4728. Min Act: -0.0002

Data Index: 741317 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4740. Min Act: -0.0001

Data Index: 371752 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4573. Min Act: -0.0002

Data Index: 1278845 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3962. Min Act: -0.0002

Data Index: 134998 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4170. Min Act: -0.0002

Data Index: 125598 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4141. Min Act: -0.0002

Data Index: 570897 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3523. Min Act: -0.0002

Data Index: 226331 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3861. Min Act: -0.0002

Data Index: 189278 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3713. Min Act: -0.0001

Data Index: 1100740 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3606. Min Act: -0.0001

Data Index: 1165359 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.4113. Min Act: -0.0002

Data Index: 1260185 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3740. Min Act: -0.0002

Data Index: 351241 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1290177 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3752. Min Act: -0.0001

Data Index: 865143 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3859. Min Act: -0.0002

Data Index: 783772 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1094842 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3606. Min Act: -0.0002

Data Index: 1216568 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3967. Min Act: -0.0001

Data Index: 425702 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.4973. Min Range: -0.4973

Max Act: 0.3597. Min Act: -0.0002

Data Index: 749072 (C4 (Web Text))

Max Activating Token Index: 551