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

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

Neuron 4012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.3274. Min Act: -0.0001

Data Index: 1133980 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.3596. Min Act: -0.0001

Data Index: 863317 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.1757. Min Act: -0.0001

Data Index: 439945 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.2114. Min Act: -0.0001

Data Index: 894614 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1346992 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1316537 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0739. Min Act: -0.0001

Data Index: 818323 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.1253. Min Act: -0.0001

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1162553 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1230824 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0668. Min Act: -0.0000

Data Index: 885383 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1103976 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0860. Min Act: -0.0000

Data Index: 165710 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0389. Min Act: -0.0000

Data Index: 601811 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0440. Min Act: -0.0001

Data Index: 637246 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0795. Min Act: -0.0001

Data Index: 1102996 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0925. Min Act: -0.0001

Data Index: 779378 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0976. Min Act: -0.0000

Data Index: 974056 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.3596. Min Range: -1.3596

Max Act: 0.9966. Min Act: -0.0000

Data Index: 89231 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.3596. Min Range: -1.3596

Max Act: 1.0560. Min Act: -0.0001

Data Index: 583318 (C4 (Web Text))

Max Activating Token Index: 421