Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3378 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1985. Min Act: -0.0001

Data Index: 11361 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.2625. Min Act: -0.0001

Data Index: 708557 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1233. Min Act: -0.0001

Data Index: 449893 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1106. Min Act: -0.0001

Data Index: 1315046 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1627. Min Act: -0.0001

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1400. Min Act: -0.0001

Data Index: 496039 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.1644. Min Act: -0.0001

Data Index: 269499 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.0882. Min Act: -0.0001

Data Index: 208038 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.0777. Min Act: -0.0001

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.0588. Min Act: -0.0001

Data Index: 456239 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9876. Min Act: -0.0001

Data Index: 398802 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 1.2625. Min Range: -1.2625

Max Act: 1.0151. Min Act: -0.0001

Data Index: 512021 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9309. Min Act: -0.0001

Data Index: 668646 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9181. Min Act: -0.0001

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9795. Min Act: -0.0001

Data Index: 849130 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9497. Min Act: -0.0001

Data Index: 898965 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.8866. Min Act: -0.0001

Data Index: 124862 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9841. Min Act: -0.0001

Data Index: 901733 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9895. Min Act: -0.0001

Data Index: 226940 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.2625. Min Range: -1.2625

Max Act: 0.9641. Min Act: -0.0001

Data Index: 546583 (C4 (Web Text))

Max Activating Token Index: 591