Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4188 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5089. Min Range: -3.5089

Max Act: 3.5089. Min Act: -0.0000

Data Index: 299208 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.5089. Min Range: -3.5089

Max Act: 3.4348. Min Act: -0.0000

Data Index: 347190 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 3.5089. Min Range: -3.5089

Max Act: 3.2384. Min Act: -0.0000

Data Index: 1087500 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 3.5089. Min Range: -3.5089

Max Act: 3.0161. Min Act: -0.0000

Data Index: 965245 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.8559. Min Act: -0.0000

Data Index: 1260779 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.9128. Min Act: -0.0000

Data Index: 823330 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7379. Min Act: -0.0000

Data Index: 701888 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.5184. Min Act: -0.0000

Data Index: 170799 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7894. Min Act: -0.0000

Data Index: 76117 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7358. Min Act: -0.0000

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7237. Min Act: -0.0000

Data Index: 1082622 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7442. Min Act: -0.0000

Data Index: 1092185 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.8645. Min Act: -0.0000

Data Index: 686194 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.7023. Min Act: -0.0000

Data Index: 1093124 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1207520 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.8162. Min Act: -0.0000

Data Index: 640132 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.6634. Min Act: -0.0000

Data Index: 333991 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.6603. Min Act: -0.0000

Data Index: 640709 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.6695. Min Act: -0.0000

Data Index: 478983 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 3.5089. Min Range: -3.5089

Max Act: 2.5195. Min Act: -0.0000

Data Index: 104130 (C4 (Web Text))

Max Activating Token Index: 824