Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2753 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1145116 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0318. Min Act: -0.0002

Data Index: 98604 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1164537 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0270. Min Act: -0.0002

Data Index: 81511 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1307098 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0266. Min Act: -0.0002

Data Index: 547517 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0263. Min Act: -0.0002

Data Index: 504509 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0261. Min Act: -0.0002

Data Index: 403134 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0261. Min Act: -0.0002

Data Index: 595065 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0256. Min Act: -0.0002

Data Index: 289152 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1091417 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0257. Min Act: -0.0002

Data Index: 180059 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1199485 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1200257 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0251. Min Act: -0.0002

Data Index: 401423 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0251. Min Act: -0.0002

Data Index: 7319 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0250. Min Act: -0.0002

Data Index: 733890 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0249. Min Act: -0.0002

Data Index: 979324 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1186082 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1121177 (C4 (Web Text))

Max Activating Token Index: 778