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

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

Neuron 3766 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: 1.6906. Min Range: -1.6906

Max Act: 1.6875. Min Act: -0.0002

Data Index: 1284458 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.6906. Min Act: -0.0002

Data Index: 631208 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.6208. Min Act: -0.0002

Data Index: 673361 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.5801. Min Act: -0.0002

Data Index: 152634 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.5233. Min Act: -0.0002

Data Index: 1036667 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.5682. Min Act: -0.0002

Data Index: 342377 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.5116. Min Act: -0.0002

Data Index: 1085467 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.4185. Min Act: -0.0002

Data Index: 389673 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.4198. Min Act: -0.0002

Data Index: 265430 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3862. Min Act: -0.0002

Data Index: 708809 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3645. Min Act: -0.0002

Data Index: 748658 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3571. Min Act: -0.0002

Data Index: 324612 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3568. Min Act: -0.0002

Data Index: 955538 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3376. Min Act: -0.0002

Data Index: 1059174 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3412. Min Act: -0.0002

Data Index: 1197740 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3236. Min Act: -0.0002

Data Index: 1359678 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3268. Min Act: -0.0002

Data Index: 1243849 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3064. Min Act: -0.0002

Data Index: 68076 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3176. Min Act: -0.0002

Data Index: 1290868 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.2806. Min Act: -0.0002

Data Index: 1252065 (C4 (Web Text))

Max Activating Token Index: 38