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

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

Neuron 1981 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0006

Data Index: 946540 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0390. Min Act: -0.0006

Data Index: 271078 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0395. Min Act: -0.0006

Data Index: 1167092 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0394. Min Act: -0.0006

Data Index: 731565 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0394. Min Act: -0.0006

Data Index: 1311917 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0384. Min Act: -0.0006

Data Index: 836024 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0391. Min Act: -0.0006

Data Index: 803856 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1259447 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0384. Min Act: -0.0006

Data Index: 1622355 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0382. Min Act: -0.0006

Data Index: 79001 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0374. Min Act: -0.0006

Data Index: 809749 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0371. Min Act: -0.0006

Data Index: 614859 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0380. Min Act: -0.0006

Data Index: 998964 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0364. Min Act: -0.0006

Data Index: 832332 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0369. Min Act: -0.0006

Data Index: 300901 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0360. Min Act: -0.0006

Data Index: 844370 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1391339 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0372. Min Act: -0.0006

Data Index: 104578 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0371. Min Act: -0.0006

Data Index: 889911 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1204099 (C4 (Web Text))

Max Activating Token Index: 130