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

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

Neuron 846 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0528. Min Range: -1.0528

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1433298 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.0528. Min Range: -1.0528

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1384724 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1614001 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1374403 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1570938 (Python Code)

Max Activating Token Index: 948

Text #5

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1596933 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1602110 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1414833 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1400451 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1613234 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1491750 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1367825 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1416202 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1376186 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1405703 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1392884 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1590825 (Python Code)

Max Activating Token Index: 899

Text #17

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1488107 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1496332 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 1.0528. Min Range: -1.0528

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1365809 (Python Code)

Max Activating Token Index: 716