Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1205 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0456. Min Act: -0.0006

Data Index: 88007 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0453. Min Act: -0.0005

Data Index: 371933 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0006

Data Index: 875440 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0415. Min Act: -0.0006

Data Index: 97728 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1293280 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0432. Min Act: -0.0006

Data Index: 343575 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1163705 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1295234 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0420. Min Act: -0.0006

Data Index: 654157 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0410. Min Act: -0.0006

Data Index: 849784 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0382. Min Act: -0.0006

Data Index: 430933 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1183122 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0403. Min Act: -0.0006

Data Index: 904805 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0406. Min Act: -0.0006

Data Index: 833934 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1336535 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0407. Min Act: -0.0006

Data Index: 649484 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1354365 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0388. Min Act: -0.0006

Data Index: 904138 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0409. Min Act: -0.0006

Data Index: 598144 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0399. Min Act: -0.0006

Data Index: 1111698 (C4 (Web Text))

Max Activating Token Index: 114