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

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

Neuron 2686 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.8449. Min Act: -0.0000

Data Index: 244309 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.5895. Min Act: -0.0000

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.2413. Min Act: -0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1219151 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.1922. Min Act: -0.0000

Data Index: 151307 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1160311 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.2222. Min Act: -0.0000

Data Index: 435262 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.1763. Min Act: -0.0000

Data Index: 651648 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1150310 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1208765 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.8449. Min Range: -1.8449

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1254147 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.8956. Min Act: -0.0000

Data Index: 75896 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9135. Min Act: -0.0000

Data Index: 901669 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9459. Min Act: -0.0000

Data Index: 975692 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9322. Min Act: -0.0000

Data Index: 608869 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9249. Min Act: -0.0000

Data Index: 812036 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1121152 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9394. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1354763 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.8449. Min Range: -1.8449

Max Act: 0.9326. Min Act: -0.0000

Data Index: 588155 (C4 (Web Text))

Max Activating Token Index: 660