Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3508 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1230666 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1783. Min Act: -0.0001

Data Index: 200434 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1239. Min Act: -0.0001

Data Index: 193548 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1585645 (Python Code)

Max Activating Token Index: 654

Text #4

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1378. Min Act: -0.0001

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1283997 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.1365. Min Act: -0.0001

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1109781 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0230. Min Act: -0.0000

Data Index: 380247 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0165. Min Act: -0.0000

Data Index: 265589 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1544027 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1394270 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1065790 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1249133 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1518234 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.0006. Min Act: -0.0001

Data Index: 72083 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9299. Min Act: -0.0000

Data Index: 292209 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9634. Min Act: -0.0000

Data Index: 91337 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1272852 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9279. Min Act: -0.0000

Data Index: 290540 (C4 (Web Text))

Max Activating Token Index: 541