Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1028035 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1154741 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0275. Min Act: -0.0006

Data Index: 968292 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0239. Min Act: -0.0006

Data Index: 225544 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0006

Data Index: 249199 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0261. Min Act: -0.0006

Data Index: 324026 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0006

Data Index: 567528 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0006

Data Index: 645869 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1026466 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0267. Min Act: -0.0006

Data Index: 979933 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0240. Min Act: -0.0006

Data Index: 583601 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1205022 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0249. Min Act: -0.0006

Data Index: 689202 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0006

Data Index: 251711 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0240. Min Act: -0.0006

Data Index: 577255 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0252. Min Act: -0.0006

Data Index: 511803 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0276. Min Act: -0.0006

Data Index: 491448 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1076510 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0006

Data Index: 204739 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0239. Min Act: -0.0006

Data Index: 496597 (C4 (Web Text))

Max Activating Token Index: 497