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

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

Neuron 2702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.9760. Min Act: -0.0000

Data Index: 199533 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8748. Min Act: -0.0001

Data Index: 394175 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8182. Min Act: -0.0001

Data Index: 826528 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1323894 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7354. Min Act: -0.0000

Data Index: 62781 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7288. Min Act: -0.0001

Data Index: 287969 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7387. Min Act: -0.0000

Data Index: 739866 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6848. Min Act: -0.0000

Data Index: 624426 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1248317 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6550. Min Act: -0.0000

Data Index: 688487 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6680. Min Act: -0.0000

Data Index: 996171 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1274698 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1324177 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6466. Min Act: -0.0000

Data Index: 398596 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1323494 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6496. Min Act: -0.0001

Data Index: 206674 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6227. Min Act: -0.0000

Data Index: 247971 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6354. Min Act: -0.0001

Data Index: 918115 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1003744 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1261289 (C4 (Web Text))

Max Activating Token Index: 972