Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 952 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 392294 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1150944 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0528. Min Act: -0.0001

Data Index: 227416 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1189667 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0490. Min Act: -0.0001

Data Index: 210477 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0488. Min Act: -0.0002

Data Index: 995435 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0477. Min Act: -0.0002

Data Index: 193677 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0483. Min Act: -0.0002

Data Index: 710875 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0471. Min Act: -0.0001

Data Index: 117553 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0470. Min Act: -0.0001

Data Index: 231937 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0462. Min Act: -0.0001

Data Index: 588298 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1339037 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0439. Min Act: -0.0002

Data Index: 104884 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0454. Min Act: -0.0001

Data Index: 988087 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1054773 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0437. Min Act: -0.0001

Data Index: 681934 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0426. Min Act: -0.0002

Data Index: 919218 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0440. Min Act: -0.0002

Data Index: 263255 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0422. Min Act: -0.0002

Data Index: 77222 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0436. Min Act: -0.0001

Data Index: 461470 (C4 (Web Text))

Max Activating Token Index: 495