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

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

Neuron 2317 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: 1.6423. Min Range: -1.6423

Max Act: 1.6423. Min Act: -0.0002

Data Index: 1623536 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.4531. Min Act: -0.0002

Data Index: 1495936 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.4484. Min Act: -0.0002

Data Index: 1553006 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.4534. Min Act: -0.0002

Data Index: 1485224 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3979. Min Act: -0.0002

Data Index: 1459121 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.4009. Min Act: -0.0002

Data Index: 1364071 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3935. Min Act: -0.0002

Data Index: 1389688 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3609. Min Act: -0.0002

Data Index: 1627508 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3746. Min Act: -0.0002

Data Index: 1529202 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3480. Min Act: -0.0002

Data Index: 1576351 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3318. Min Act: -0.0002

Data Index: 1647786 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3352. Min Act: -0.0002

Data Index: 1489233 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3340. Min Act: -0.0002

Data Index: 1588034 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3513. Min Act: -0.0002

Data Index: 1617810 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3343. Min Act: -0.0002

Data Index: 1417108 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3223. Min Act: -0.0002

Data Index: 1617288 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3223. Min Act: -0.0002

Data Index: 1481832 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3378. Min Act: -0.0002

Data Index: 1622191 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3073. Min Act: -0.0002

Data Index: 1570597 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 1.6423. Min Range: -1.6423

Max Act: 1.3247. Min Act: -0.0002

Data Index: 1552358 (Python Code)

Max Activating Token Index: 817