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

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

Neuron 4583 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: 2.1398. Min Range: -2.1398

Max Act: 2.1398. Min Act: -0.0002

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.0722. Min Act: -0.0002

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.0992. Min Act: -0.0002

Data Index: 1153521 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.0034. Min Act: -0.0002

Data Index: 379927 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.0028. Min Act: -0.0002

Data Index: 509439 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9638. Min Act: -0.0002

Data Index: 844058 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.0146. Min Act: -0.0002

Data Index: 1243613 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9340. Min Act: -0.0002

Data Index: 1072669 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9503. Min Act: -0.0002

Data Index: 344871 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8974. Min Act: -0.0002

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9673. Min Act: -0.0002

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9178. Min Act: -0.0003

Data Index: 1204265 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9441. Min Act: -0.0002

Data Index: 706322 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8287. Min Act: -0.0002

Data Index: 1278177 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9095. Min Act: -0.0003

Data Index: 1081033 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8368. Min Act: -0.0002

Data Index: 1344819 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9190. Min Act: -0.0002

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9092. Min Act: -0.0002

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8163. Min Act: -0.0003

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8104. Min Act: -0.0002

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 748