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

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

Neuron 5942 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2953. Min Act: -0.0001

Data Index: 1572485 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1476559 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1374416 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1574073 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2765. Min Act: -0.0001

Data Index: 1391833 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2709. Min Act: -0.0001

Data Index: 1438349 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1630405 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1515445 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1549228 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1458602 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1535396 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1606565 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1384952 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1413389 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1554496 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1591802 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2467. Min Act: -0.0001

Data Index: 1627957 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1653178 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1532426 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1538180 (Python Code)

Max Activating Token Index: 163