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

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

Neuron 3881 in Layer 1

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: 1.4361. Min Range: -1.4361

Max Act: 1.4361. Min Act: -0.0002

Data Index: 1405174 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3766. Min Act: -0.0002

Data Index: 1645769 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3824. Min Act: -0.0002

Data Index: 1367074 (Python Code)

Max Activating Token Index: 1007

Text #3

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3575. Min Act: -0.0002

Data Index: 1447758 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3597. Min Act: -0.0002

Data Index: 1504723 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3875. Min Act: -0.0002

Data Index: 1540325 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3837. Min Act: -0.0002

Data Index: 1513794 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3605. Min Act: -0.0002

Data Index: 1485932 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3562. Min Act: -0.0002

Data Index: 1427935 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3419. Min Act: -0.0002

Data Index: 1406401 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3296. Min Act: -0.0002

Data Index: 1507359 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3276. Min Act: -0.0002

Data Index: 1575292 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3473. Min Act: -0.0002

Data Index: 1576686 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3477. Min Act: -0.0002

Data Index: 1435233 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3384. Min Act: -0.0002

Data Index: 1362042 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3166. Min Act: -0.0002

Data Index: 1386570 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3358. Min Act: -0.0002

Data Index: 1413716 (Python Code)

Max Activating Token Index: 958

Text #17

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3345. Min Act: -0.0002

Data Index: 1439607 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3502. Min Act: -0.0002

Data Index: 1585791 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 1.4361. Min Range: -1.4361

Max Act: 1.3240. Min Act: -0.0002

Data Index: 1393167 (Python Code)

Max Activating Token Index: 834