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

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

Neuron 3392 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.9413. Min Act: -0.0001

Data Index: 883027 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8768. Min Act: -0.0001

Data Index: 801697 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8972. Min Act: -0.0001

Data Index: 25932 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8319. Min Act: -0.0001

Data Index: 135274 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.8385. Min Act: -0.0001

Data Index: 346782 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7647. Min Act: -0.0001

Data Index: 287492 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7176. Min Act: -0.0001

Data Index: 744289 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1026448 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7149. Min Act: -0.0001

Data Index: 221580 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1140202 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1163619 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7124. Min Act: -0.0001

Data Index: 347760 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7944. Min Act: -0.0001

Data Index: 851011 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7781. Min Act: -0.0001

Data Index: 366719 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7256. Min Act: -0.0001

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7441. Min Act: -0.0001

Data Index: 929608 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7109. Min Act: -0.0001

Data Index: 130713 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.7407. Min Act: -0.0001

Data Index: 882435 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1344617 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.4851. Min Act: -0.0001

Data Index: 774104 (C4 (Web Text))

Max Activating Token Index: 564