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

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

Neuron 3391 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: 2.0250. Min Range: -2.0250

Max Act: 2.0250. Min Act: -0.0002

Data Index: 1260377 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.9948. Min Act: -0.0002

Data Index: 909504 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.9783. Min Act: -0.0002

Data Index: 368015 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8486. Min Act: -0.0002

Data Index: 541843 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8794. Min Act: -0.0002

Data Index: 726933 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8371. Min Act: -0.0002

Data Index: 777607 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8233. Min Act: -0.0002

Data Index: 624874 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8075. Min Act: -0.0002

Data Index: 420764 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8282. Min Act: -0.0002

Data Index: 1071480 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8125. Min Act: -0.0002

Data Index: 745544 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7246. Min Act: -0.0002

Data Index: 876895 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7841. Min Act: -0.0002

Data Index: 547668 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7591. Min Act: -0.0002

Data Index: 441819 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7200. Min Act: -0.0002

Data Index: 243979 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7502. Min Act: -0.0002

Data Index: 798909 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7072. Min Act: -0.0002

Data Index: 148268 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7326. Min Act: -0.0002

Data Index: 522953 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6955. Min Act: -0.0002

Data Index: 1186033 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7371. Min Act: -0.0002

Data Index: 190835 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6997. Min Act: -0.0002

Data Index: 567044 (C4 (Web Text))

Max Activating Token Index: 283