Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1389 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0114. Min Range: -1.0114

Max Act: 1.0114. Min Act: -0.0001

Data Index: 1052228 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9803. Min Act: -0.0001

Data Index: 399245 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7011. Min Act: -0.0001

Data Index: 1190929 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8900. Min Act: -0.0001

Data Index: 1186997 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7692. Min Act: -0.0001

Data Index: 982264 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7381. Min Act: -0.0001

Data Index: 631234 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8118. Min Act: -0.0001

Data Index: 413566 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8020. Min Act: -0.0001

Data Index: 911704 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7328. Min Act: -0.0001

Data Index: 901841 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7976. Min Act: -0.0001

Data Index: 910765 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1591494 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7170. Min Act: -0.0001

Data Index: 182834 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7424. Min Act: -0.0001

Data Index: 826060 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1026561 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1066745 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7494. Min Act: -0.0001

Data Index: 130771 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1329238 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1505145 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.6665. Min Act: -0.0001

Data Index: 309032 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.6937. Min Act: -0.0001

Data Index: 511118 (C4 (Web Text))

Max Activating Token Index: 754