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

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

Neuron 5574 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1575. Min Act: -0.0000

Data Index: 74722 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1724. Min Act: -0.0000

Data Index: 272793 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1622. Min Act: -0.0000

Data Index: 526659 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0215. Min Act: -0.0000

Data Index: 661063 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1034. Min Act: 0.0000

Data Index: 90987 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0278. Min Act: -0.0000

Data Index: 877088 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.0310. Min Act: -0.0000

Data Index: 167245 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8880. Min Act: 0.0000

Data Index: 1063309 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9522. Min Act: -0.0000

Data Index: 794944 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9399. Min Act: -0.0000

Data Index: 709169 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9290. Min Act: -0.0000

Data Index: 152178 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9322. Min Act: -0.0000

Data Index: 405348 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8574. Min Act: -0.0000

Data Index: 758469 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8995. Min Act: -0.0000

Data Index: 873913 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9025. Min Act: -0.0000

Data Index: 535272 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.9002. Min Act: -0.0000

Data Index: 167276 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1076131 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1498 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8863. Min Act: 0.0000

Data Index: 744777 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8998. Min Act: 0.0000

Data Index: 494444 (C4 (Web Text))

Max Activating Token Index: 837