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

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

Neuron 2627 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: 1.0041. Min Range: -1.0041

Max Act: 1.0041. Min Act: -0.0002

Data Index: 1181375 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.9527. Min Act: -0.0002

Data Index: 78742 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8718. Min Act: -0.0002

Data Index: 840979 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8689. Min Act: -0.0002

Data Index: 1233061 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8422. Min Act: -0.0002

Data Index: 519361 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8565. Min Act: -0.0002

Data Index: 1352061 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8476. Min Act: -0.0002

Data Index: 991378 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8324. Min Act: -0.0002

Data Index: 422031 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8294. Min Act: -0.0002

Data Index: 1122721 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8412. Min Act: -0.0002

Data Index: 1312428 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8336. Min Act: -0.0002

Data Index: 478424 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8406. Min Act: -0.0002

Data Index: 729182 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8452. Min Act: -0.0002

Data Index: 1314217 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8327. Min Act: -0.0002

Data Index: 1255101 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8137. Min Act: -0.0002

Data Index: 575907 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8260. Min Act: -0.0002

Data Index: 239905 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8213. Min Act: -0.0003

Data Index: 1117335 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8225. Min Act: -0.0002

Data Index: 1262348 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8201. Min Act: -0.0002

Data Index: 999470 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.0041. Min Range: -1.0041

Max Act: 0.8008. Min Act: -0.0002

Data Index: 351070 (C4 (Web Text))

Max Activating Token Index: 60