Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3933 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0002

Data Index: 316699 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1137530 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0492. Min Act: -0.0002

Data Index: 329825 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0428. Min Act: -0.0002

Data Index: 613708 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0464. Min Act: -0.0002

Data Index: 74779 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0405. Min Act: -0.0002

Data Index: 607735 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0410. Min Act: -0.0002

Data Index: 399210 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0431. Min Act: -0.0002

Data Index: 359508 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1237250 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0437. Min Act: -0.0002

Data Index: 137192 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0428. Min Act: -0.0002

Data Index: 700915 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0428. Min Act: -0.0002

Data Index: 795428 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0389. Min Act: -0.0002

Data Index: 45205 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0356. Min Act: -0.0002

Data Index: 106777 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0373. Min Act: -0.0002

Data Index: 878996 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1283049 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0421. Min Act: -0.0002

Data Index: 436876 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0388. Min Act: -0.0002

Data Index: 109666 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0389. Min Act: -0.0002

Data Index: 844728 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1286887 (C4 (Web Text))

Max Activating Token Index: 44