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

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

Neuron 3218 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: 2.0041. Min Range: -2.0041

Max Act: 2.0041. Min Act: -0.0002

Data Index: 441594 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5857. Min Act: -0.0002

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5712. Min Act: -0.0002

Data Index: 1367556 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5453. Min Act: -0.0003

Data Index: 563839 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5672. Min Act: -0.0002

Data Index: 1253917 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5921. Min Act: -0.0002

Data Index: 553160 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.5157. Min Act: -0.0002

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4889. Min Act: -0.0002

Data Index: 1329963 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4429. Min Act: -0.0002

Data Index: 76043 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4765. Min Act: -0.0002

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4649. Min Act: -0.0002

Data Index: 868217 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4319. Min Act: -0.0002

Data Index: 671920 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4408. Min Act: -0.0002

Data Index: 380196 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3928. Min Act: -0.0002

Data Index: 1276300 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3845. Min Act: -0.0002

Data Index: 968329 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3725. Min Act: -0.0002

Data Index: 1186625 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3981. Min Act: -0.0002

Data Index: 1181351 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3957. Min Act: -0.0002

Data Index: 1116630 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.4022. Min Act: -0.0002

Data Index: 101857 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 2.0041. Min Range: -2.0041

Max Act: 1.3740. Min Act: -0.0002

Data Index: 166877 (C4 (Web Text))

Max Activating Token Index: 70