Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.7092. Min Act: -0.0000

Data Index: 291970 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6621. Min Act: -0.0000

Data Index: 920590 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1140886 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.7099. Min Act: -0.0000

Data Index: 438333 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5875. Min Act: -0.0000

Data Index: 274459 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.7310. Min Act: -0.0000

Data Index: 34881 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1046844 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1125504 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1621631 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1506054 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1206366 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6113. Min Act: -0.0000

Data Index: 148262 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5952. Min Act: -0.0000

Data Index: 621294 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5882. Min Act: -0.0000

Data Index: 276227 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.6021. Min Act: -0.0000

Data Index: 933702 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5448. Min Act: -0.0000

Data Index: 295932 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5557. Min Act: -0.0000

Data Index: 779161 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5808. Min Act: -0.0000

Data Index: 103584 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1171818 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.7310. Min Range: -0.7310

Max Act: 0.5649. Min Act: -0.0000

Data Index: 248337 (C4 (Web Text))

Max Activating Token Index: 321