Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2643 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.2543. Min Act: -0.0001

Data Index: 812473 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.2627. Min Act: -0.0001

Data Index: 107954 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1912. Min Act: -0.0001

Data Index: 904 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1762. Min Act: -0.0002

Data Index: 23737 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1764. Min Act: -0.0001

Data Index: 671906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1385. Min Act: -0.0001

Data Index: 94774 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1190. Min Act: -0.0001

Data Index: 459652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1340. Min Act: -0.0001

Data Index: 492354 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1279. Min Act: -0.0001

Data Index: 287980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1219. Min Act: -0.0001

Data Index: 27506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1236. Min Act: -0.0001

Data Index: 1309535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1118. Min Act: -0.0001

Data Index: 1614852 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.0944. Min Act: -0.0001

Data Index: 25722 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1078. Min Act: -0.0001

Data Index: 823343 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.0970. Min Act: -0.0001

Data Index: 69447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1022. Min Act: -0.0002

Data Index: 1167621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.0876. Min Act: -0.0001

Data Index: 1062145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1085. Min Act: -0.0001

Data Index: 1310825 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.1079. Min Act: -0.0001

Data Index: 279036 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.2627. Min Range: -1.2627

Max Act: 1.0906. Min Act: -0.0001

Data Index: 1197410 (C4 (Web Text))

Max Activating Token Index: 1023