Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0438. Min Act: -0.0005

Data Index: 1120934 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1289521 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0453. Min Act: -0.0005

Data Index: 490224 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0005

Data Index: 774001 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0442. Min Act: -0.0005

Data Index: 826750 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1359475 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0401. Min Act: -0.0005

Data Index: 873807 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0418. Min Act: -0.0005

Data Index: 933641 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0401. Min Act: -0.0005

Data Index: 863874 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1219909 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0403. Min Act: -0.0005

Data Index: 283519 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0409. Min Act: -0.0005

Data Index: 281416 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0395. Min Act: -0.0005

Data Index: 98443 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0424. Min Act: -0.0005

Data Index: 144436 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0398. Min Act: -0.0005

Data Index: 346886 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0452. Min Act: -0.0005

Data Index: 600774 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1145414 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0402. Min Act: -0.0005

Data Index: 771627 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1047562 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0397. Min Act: -0.0005

Data Index: 175466 (C4 (Web Text))

Max Activating Token Index: 536