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

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

Neuron 814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.6951. Min Act: -0.0000

Data Index: 909514 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.2607. Min Act: -0.0000

Data Index: 1348824 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.3762. Min Act: -0.0000

Data Index: 381874 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.2405. Min Act: -0.0000

Data Index: 964815 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.1107. Min Act: -0.0000

Data Index: 1029955 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.8651. Min Act: -0.0000

Data Index: 630805 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 2.6951. Min Range: -2.6951

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1178974 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.9373. Min Act: -0.0000

Data Index: 592057 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.7393. Min Act: -0.0000

Data Index: 193674 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1009330 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.7600. Min Act: -0.0000

Data Index: 1236577 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.8340. Min Act: -0.0000

Data Index: 1062132 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1253380 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.7808. Min Act: -0.0000

Data Index: 503753 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.8793. Min Act: -0.0000

Data Index: 731874 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.6603. Min Act: -0.0000

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.6613. Min Act: -0.0000

Data Index: 24518 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1133998 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.7277. Min Act: -0.0000

Data Index: 1100708 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.6951. Min Range: -2.6951

Max Act: 1.7104. Min Act: -0.0000

Data Index: 892240 (C4 (Web Text))

Max Activating Token Index: 430