Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 947 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0002

Data Index: 1339130 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6368. Min Act: -0.0002

Data Index: 688254 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6040. Min Act: -0.0002

Data Index: 591091 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6016. Min Act: -0.0002

Data Index: 467277 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6126. Min Act: -0.0001

Data Index: 182194 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1474574 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5657. Min Act: -0.0002

Data Index: 19002 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5653. Min Act: -0.0002

Data Index: 1231600 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5556. Min Act: -0.0002

Data Index: 1080510 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5398. Min Act: -0.0002

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5539. Min Act: -0.0002

Data Index: 1267449 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5508. Min Act: -0.0002

Data Index: 813695 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5478. Min Act: -0.0002

Data Index: 1116305 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1534125 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5401. Min Act: -0.0001

Data Index: 1453487 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5495. Min Act: -0.0002

Data Index: 1238040 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5275. Min Act: -0.0002

Data Index: 1130401 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5476. Min Act: -0.0002

Data Index: 703070 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5293. Min Act: -0.0002

Data Index: 719073 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1337530 (C4 (Web Text))

Max Activating Token Index: 928