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

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

Neuron 1848 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: 1.3895. Min Range: -1.3895

Max Act: 1.3895. Min Act: -0.0002

Data Index: 656134 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.3730. Min Act: -0.0001

Data Index: 900507 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.3145. Min Act: -0.0002

Data Index: 934489 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2941. Min Act: -0.0002

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2850. Min Act: -0.0002

Data Index: 771526 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2269. Min Act: -0.0001

Data Index: 726742 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2304. Min Act: -0.0001

Data Index: 259018 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2431. Min Act: -0.0001

Data Index: 1167936 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1996. Min Act: -0.0001

Data Index: 1277748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1552. Min Act: -0.0001

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1329. Min Act: -0.0001

Data Index: 589081 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2278. Min Act: -0.0001

Data Index: 1020246 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2188. Min Act: -0.0001

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.2237. Min Act: -0.0001

Data Index: 806215 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1655. Min Act: -0.0001

Data Index: 571705 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1309. Min Act: -0.0002

Data Index: 188631 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1756. Min Act: -0.0001

Data Index: 1346842 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1492. Min Act: -0.0002

Data Index: 958375 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.1107. Min Act: -0.0002

Data Index: 1045939 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.3895. Min Range: -1.3895

Max Act: 1.0947. Min Act: -0.0002

Data Index: 32163 (C4 (Web Text))

Max Activating Token Index: 921