Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 7.6886. Min Range: -7.6886

Max Act: 6.9181. Min Act: -0.0001

Data Index: 278053 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 7.6886. Min Range: -7.6886

Max Act: 7.1377. Min Act: -0.0001

Data Index: 75443 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 7.6886. Min Range: -7.6886

Max Act: 7.6886. Min Act: -0.0001

Data Index: 1073185 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.7773. Min Act: -0.0001

Data Index: 653041 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.8587. Min Act: -0.0001

Data Index: 512660 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.7127. Min Act: -0.0001

Data Index: 145574 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.5057. Min Act: -0.0001

Data Index: 1323634 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.6461. Min Act: -0.0001

Data Index: 786670 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 7.6886. Min Range: -7.6886

Max Act: 4.9515. Min Act: -0.0001

Data Index: 111882 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.3033. Min Act: -0.0001

Data Index: 1316956 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.4547. Min Act: -0.0001

Data Index: 542705 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.2903. Min Act: -0.0001

Data Index: 1292564 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 7.6886. Min Range: -7.6886

Max Act: 6.2305. Min Act: -0.0001

Data Index: 1014150 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.2318. Min Act: -0.0001

Data Index: 41436 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.2735. Min Act: -0.0001

Data Index: 857313 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.1371. Min Act: -0.0001

Data Index: 877338 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.2578. Min Act: -0.0001

Data Index: 421724 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.3816. Min Act: -0.0001

Data Index: 936309 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.0503. Min Act: -0.0001

Data Index: 982233 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 7.6886. Min Range: -7.6886

Max Act: 5.0019. Min Act: -0.0001

Data Index: 1079877 (C4 (Web Text))

Max Activating Token Index: 604