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

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

Neuron 4155 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: 0.7298. Min Range: -0.7298

Max Act: 0.7298. Min Act: -0.0002

Data Index: 1162822 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5967. Min Act: -0.0002

Data Index: 695701 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5875. Min Act: -0.0002

Data Index: 1358409 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5493. Min Act: -0.0002

Data Index: 156213 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5297. Min Act: -0.0002

Data Index: 892203 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5413. Min Act: -0.0002

Data Index: 1323872 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5231. Min Act: -0.0002

Data Index: 1288060 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5398. Min Act: -0.0002

Data Index: 265386 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5251. Min Act: -0.0002

Data Index: 526005 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5315. Min Act: -0.0002

Data Index: 298701 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5051. Min Act: -0.0002

Data Index: 771149 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5135. Min Act: -0.0002

Data Index: 1198047 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5038. Min Act: -0.0002

Data Index: 422678 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5070. Min Act: -0.0002

Data Index: 1110481 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5151. Min Act: -0.0002

Data Index: 281200 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5035. Min Act: -0.0002

Data Index: 354920 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5006. Min Act: -0.0002

Data Index: 255985 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5152. Min Act: -0.0002

Data Index: 698618 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.5013. Min Act: -0.0002

Data Index: 355059 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4973. Min Act: -0.0002

Data Index: 1016904 (C4 (Web Text))

Max Activating Token Index: 106