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

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

Neuron 4632 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: 0.8386. Min Range: -0.8386

Max Act: 0.8386. Min Act: -0.0002

Data Index: 1023532 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8262. Min Act: -0.0002

Data Index: 1189968 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8193. Min Act: -0.0002

Data Index: 139662 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8183. Min Act: -0.0002

Data Index: 1063847 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8172. Min Act: -0.0002

Data Index: 886827 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8120. Min Act: -0.0002

Data Index: 214789 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8042. Min Act: -0.0002

Data Index: 506119 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7990. Min Act: -0.0002

Data Index: 267548 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7929. Min Act: -0.0002

Data Index: 11650 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8028. Min Act: -0.0002

Data Index: 187461 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7777. Min Act: -0.0002

Data Index: 175093 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7745. Min Act: -0.0002

Data Index: 959380 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7721. Min Act: -0.0002

Data Index: 469764 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7429. Min Act: -0.0002

Data Index: 417375 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7350. Min Act: -0.0002

Data Index: 792085 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7183. Min Act: -0.0002

Data Index: 287221 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7335. Min Act: -0.0003

Data Index: 655691 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7274. Min Act: -0.0002

Data Index: 1347132 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6926. Min Act: -0.0002

Data Index: 1101484 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7111. Min Act: -0.0002

Data Index: 977960 (C4 (Web Text))

Max Activating Token Index: 12