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

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

Neuron 2615 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: 2.4663. Min Range: -2.4663

Max Act: 2.4663. Min Act: -0.0002

Data Index: 718270 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.4436. Min Act: -0.0002

Data Index: 485846 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.1347. Min Act: -0.0002

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.1385. Min Act: -0.0002

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.0899. Min Act: -0.0002

Data Index: 572045 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.1272. Min Act: -0.0002

Data Index: 1056031 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.0316. Min Act: -0.0002

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.9985. Min Act: -0.0002

Data Index: 1211792 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.0419. Min Act: -0.0002

Data Index: 90044 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.0568. Min Act: -0.0002

Data Index: 130348 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 2.4663. Min Range: -2.4663

Max Act: 2.0119. Min Act: -0.0002

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.9665. Min Act: -0.0002

Data Index: 405537 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.9293. Min Act: -0.0002

Data Index: 371668 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.9414. Min Act: -0.0002

Data Index: 530508 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.8702. Min Act: -0.0002

Data Index: 1176443 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.8897. Min Act: -0.0002

Data Index: 953351 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.8799. Min Act: -0.0002

Data Index: 670656 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.8746. Min Act: -0.0002

Data Index: 235054 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.8476. Min Act: -0.0002

Data Index: 989306 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 2.4663. Min Range: -2.4663

Max Act: 1.9257. Min Act: -0.0002

Data Index: 1155531 (C4 (Web Text))

Max Activating Token Index: 845