Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2039 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3628. Min Act: -0.0001

Data Index: 1232405 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.4844. Min Act: -0.0001

Data Index: 767754 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3284. Min Act: -0.0001

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.4306. Min Act: -0.0001

Data Index: 222111 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.5521. Min Act: -0.0001

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.4039. Min Act: -0.0001

Data Index: 1257701 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.2491. Min Act: -0.0001

Data Index: 1114963 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3779. Min Act: -0.0001

Data Index: 926441 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.1356. Min Act: -0.0001

Data Index: 1315189 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.1122. Min Act: -0.0001

Data Index: 296040 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.3753. Min Act: -0.0001

Data Index: 958549 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.2363. Min Act: -0.0001

Data Index: 652088 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.0936. Min Act: -0.0001

Data Index: 554135 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.2197. Min Act: -0.0001

Data Index: 623386 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.0548. Min Act: -0.0001

Data Index: 1294085 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.1715. Min Act: -0.0001

Data Index: 1293611 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.1567. Min Act: -0.0001

Data Index: 649570 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.0670. Min Act: -0.0001

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.0692. Min Act: -0.0001

Data Index: 1198985 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.5521. Min Range: -3.5521

Max Act: 3.0381. Min Act: -0.0001

Data Index: 1063626 (C4 (Web Text))

Max Activating Token Index: 503