Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 511 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3728. Min Act: -0.0001

Data Index: 353373 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3131. Min Act: -0.0001

Data Index: 958974 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3000. Min Act: -0.0001

Data Index: 546036 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2820. Min Act: -0.0001

Data Index: 482545 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1271601 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2702. Min Act: -0.0001

Data Index: 507502 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2509. Min Act: -0.0001

Data Index: 757849 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1061585 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2450. Min Act: -0.0001

Data Index: 506686 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2460. Min Act: -0.0001

Data Index: 327327 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2423. Min Act: -0.0001

Data Index: 650760 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2446. Min Act: -0.0001

Data Index: 788641 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2229. Min Act: -0.0001

Data Index: 613151 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2407. Min Act: -0.0001

Data Index: 251664 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2403. Min Act: -0.0001

Data Index: 591966 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2454. Min Act: -0.0001

Data Index: 434059 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2325. Min Act: -0.0001

Data Index: 314809 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2263. Min Act: -0.0001

Data Index: 845144 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2274. Min Act: -0.0001

Data Index: 256255 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2337. Min Act: -0.0001

Data Index: 421140 (C4 (Web Text))

Max Activating Token Index: 828