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

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

Neuron 3263 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1387. Min Range: -5.1387

Max Act: 5.0670. Min Act: -0.0001

Data Index: 1194131 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 5.1387. Min Range: -5.1387

Max Act: 5.1387. Min Act: -0.0001

Data Index: 701005 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.9841. Min Act: -0.0001

Data Index: 176932 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.9537. Min Act: -0.0001

Data Index: 103677 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.8521. Min Act: -0.0001

Data Index: 92921 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 5.1387. Min Range: -5.1387

Max Act: 5.0161. Min Act: -0.0001

Data Index: 1278700 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.9496. Min Act: -0.0001

Data Index: 237550 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.5487. Min Act: -0.0001

Data Index: 70448 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4287. Min Act: -0.0001

Data Index: 1025787 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.5664. Min Act: -0.0001

Data Index: 1205256 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4978. Min Act: -0.0001

Data Index: 508180 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4461. Min Act: -0.0001

Data Index: 628240 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4104. Min Act: -0.0001

Data Index: 1342926 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4280. Min Act: -0.0001

Data Index: 878391 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.3769. Min Act: -0.0001

Data Index: 227458 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.5156. Min Act: -0.0001

Data Index: 309476 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.2164. Min Act: -0.0001

Data Index: 776012 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.5465. Min Act: -0.0001

Data Index: 354438 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.4990. Min Act: -0.0001

Data Index: 965715 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 5.1387. Min Range: -5.1387

Max Act: 4.1364. Min Act: -0.0001

Data Index: 528506 (C4 (Web Text))

Max Activating Token Index: 559