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

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

Neuron 2014 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: 0.3682. Min Range: -0.3682

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1150088 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3578. Min Act: -0.0001

Data Index: 1126230 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3392. Min Act: -0.0001

Data Index: 786724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1289193 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3260. Min Act: -0.0001

Data Index: 846371 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3269. Min Act: -0.0001

Data Index: 1341753 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3227. Min Act: -0.0001

Data Index: 508110 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3232. Min Act: -0.0001

Data Index: 858891 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3272. Min Act: -0.0001

Data Index: 1094068 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1013476 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1152909 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3262. Min Act: -0.0001

Data Index: 1025834 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3264. Min Act: -0.0001

Data Index: 274184 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1135300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3204. Min Act: -0.0001

Data Index: 366936 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3255. Min Act: -0.0001

Data Index: 768506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3226. Min Act: -0.0001

Data Index: 825678 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3143. Min Act: -0.0001

Data Index: 375401 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1120268 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3682. Min Range: -0.3682

Max Act: 0.3172. Min Act: -0.0002

Data Index: 256737 (C4 (Web Text))

Max Activating Token Index: 113