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

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

Neuron 4625 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: 2.9582. Min Range: -2.9582

Max Act: 2.9582. Min Act: -0.0000

Data Index: 1270271 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 2.9582. Min Range: -2.9582

Max Act: 2.4108. Min Act: -0.0000

Data Index: 1237162 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.9650. Min Act: -0.0000

Data Index: 257375 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.8601. Min Act: -0.0000

Data Index: 740458 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.9569. Min Act: -0.0000

Data Index: 108683 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.6779. Min Act: -0.0000

Data Index: 143665 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.5539. Min Act: -0.0000

Data Index: 26807 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.6323. Min Act: -0.0000

Data Index: 822361 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.6165. Min Act: -0.0000

Data Index: 56681 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1317378 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1221794 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.4203. Min Act: -0.0000

Data Index: 141039 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1097371 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.3982. Min Act: -0.0000

Data Index: 409708 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.5737. Min Act: -0.0000

Data Index: 1250168 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.4490. Min Act: -0.0000

Data Index: 304959 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.3523. Min Act: -0.0000

Data Index: 471673 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.4864. Min Act: -0.0000

Data Index: 3704 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.3967. Min Act: -0.0000

Data Index: 394204 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 2.9582. Min Range: -2.9582

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1169464 (C4 (Web Text))

Max Activating Token Index: 235