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

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

Neuron 5231 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: 1.6225. Min Range: -1.6225

Max Act: 1.6225. Min Act: -0.0002

Data Index: 766198 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4746. Min Act: -0.0002

Data Index: 204358 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4759. Min Act: -0.0002

Data Index: 1177158 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4424. Min Act: -0.0002

Data Index: 12450 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4421. Min Act: -0.0003

Data Index: 300625 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4428. Min Act: -0.0002

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4319. Min Act: -0.0002

Data Index: 734443 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4114. Min Act: -0.0002

Data Index: 1125614 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4215. Min Act: -0.0002

Data Index: 281554 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4428. Min Act: -0.0002

Data Index: 549332 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4134. Min Act: -0.0002

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3775. Min Act: -0.0002

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4232. Min Act: -0.0002

Data Index: 566335 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4054. Min Act: -0.0002

Data Index: 1145473 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.4001. Min Act: -0.0002

Data Index: 324868 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3998. Min Act: -0.0002

Data Index: 745225 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3670. Min Act: -0.0002

Data Index: 351488 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3857. Min Act: -0.0002

Data Index: 137728 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3578. Min Act: -0.0002

Data Index: 553040 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.6225. Min Range: -1.6225

Max Act: 1.3665. Min Act: -0.0002

Data Index: 1048947 (C4 (Web Text))

Max Activating Token Index: 12