Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3962 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.5444. Min Act: -0.0001

Data Index: 1550595 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.4295. Min Act: -0.0001

Data Index: 1429226 (Python Code)

Max Activating Token Index: 892

Text #2

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3526. Min Act: -0.0001

Data Index: 1436402 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3571. Min Act: -0.0001

Data Index: 1641397 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2885. Min Act: -0.0001

Data Index: 1655675 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3232. Min Act: -0.0001

Data Index: 1615117 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1641. Min Act: -0.0001

Data Index: 1602106 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3134. Min Act: -0.0001

Data Index: 1652965 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3411. Min Act: -0.0001

Data Index: 1449434 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1427689 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2926. Min Act: -0.0001

Data Index: 1476015 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2911. Min Act: -0.0001

Data Index: 1404936 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.3008. Min Act: -0.0000

Data Index: 1434944 (Python Code)

Max Activating Token Index: 939

Text #13

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2307. Min Act: -0.0001

Data Index: 1576147 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.1615. Min Act: -0.0001

Data Index: 1627650 (Python Code)

Max Activating Token Index: 852

Text #15

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2302. Min Act: -0.0001

Data Index: 1588241 (Python Code)

Max Activating Token Index: 852

Text #16

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2710. Min Act: -0.0001

Data Index: 1398164 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1605359 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2237. Min Act: -0.0001

Data Index: 1370997 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 1.5444. Min Range: -1.5444

Max Act: 1.2963. Min Act: -0.0001

Data Index: 1379621 (Python Code)

Max Activating Token Index: 983