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

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

Neuron 5774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.1625. Min Act: -0.0000

Data Index: 509888 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.1338. Min Act: -0.0001

Data Index: 871987 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0786. Min Act: -0.0001

Data Index: 937438 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1066589 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0329. Min Act: -0.0001

Data Index: 515906 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9690. Min Act: -0.0001

Data Index: 134093 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 1.1625. Min Range: -1.1625

Max Act: 1.0190. Min Act: -0.0001

Data Index: 526709 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9547. Min Act: -0.0000

Data Index: 659886 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9847. Min Act: -0.0000

Data Index: 477065 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1248373 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9170. Min Act: -0.0000

Data Index: 830141 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9651. Min Act: -0.0001

Data Index: 1261584 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9855. Min Act: -0.0000

Data Index: 116568 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9727. Min Act: -0.0001

Data Index: 624632 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.9625. Min Act: -0.0001

Data Index: 366716 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8367. Min Act: -0.0001

Data Index: 718029 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8921. Min Act: -0.0001

Data Index: 1268025 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8059. Min Act: -0.0001

Data Index: 884492 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8166. Min Act: -0.0001

Data Index: 637538 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.1625. Min Range: -1.1625

Max Act: 0.8636. Min Act: -0.0001

Data Index: 608414 (C4 (Web Text))

Max Activating Token Index: 132