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

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

Neuron 4274 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4340. Min Range: -2.4340

Max Act: 2.4340. Min Act: -0.0000

Data Index: 288880 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.7037. Min Act: -0.0000

Data Index: 963254 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1339809 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1279645 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1167527 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.7615. Min Act: -0.0000

Data Index: 670485 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5884. Min Act: -0.0000

Data Index: 332958 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.6078. Min Act: -0.0000

Data Index: 325158 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5068. Min Act: -0.0000

Data Index: 1271638 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1232709 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.6035. Min Act: -0.0000

Data Index: 169897 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.6931. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5761. Min Act: -0.0000

Data Index: 192916 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5652. Min Act: -0.0000

Data Index: 596847 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.4271. Min Act: -0.0000

Data Index: 766685 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1215719 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.4025. Min Act: -0.0000

Data Index: 641224 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.5183. Min Act: -0.0000

Data Index: 709720 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.3643. Min Act: -0.0000

Data Index: 799797 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 2.4340. Min Range: -2.4340

Max Act: 1.3078. Min Act: -0.0000

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 53