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

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

Neuron 4769 in Layer 1

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: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1520298 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1620940 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1212205 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1575383 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1422976 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1499970 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1507842 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1375545 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1067298 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0253. Min Act: -0.0002

Data Index: 556200 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0224. Min Act: -0.0002

Data Index: 681528 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1059461 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1334267 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0214. Min Act: -0.0002

Data Index: 94039 (C4 (Web Text))

Max Activating Token Index: 716