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

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

Neuron 4971 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.5627. Min Act: -0.0000

Data Index: 1071614 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.6851. Min Act: -0.0000

Data Index: 969216 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.5338. Min Act: -0.0000

Data Index: 224191 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.8690. Min Act: -0.0000

Data Index: 483097 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.2485. Min Act: -0.0000

Data Index: 950635 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 6.8690. Min Range: -6.8690

Max Act: 6.3922. Min Act: -0.0000

Data Index: 1123680 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 6.8690. Min Range: -6.8690

Max Act: 5.9978. Min Act: -0.0000

Data Index: 1043239 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 6.8690. Min Range: -6.8690

Max Act: 5.3683. Min Act: -0.0000

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 6.8690. Min Range: -6.8690

Max Act: 5.1220. Min Act: -0.0000

Data Index: 473942 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 6.8690. Min Range: -6.8690

Max Act: 5.2717. Min Act: -0.0000

Data Index: 917901 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 6.8690. Min Range: -6.8690

Max Act: 5.0838. Min Act: -0.0000

Data Index: 721747 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 6.8690. Min Range: -6.8690

Max Act: 4.8746. Min Act: -0.0000

Data Index: 859560 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 6.8690. Min Range: -6.8690

Max Act: 4.7042. Min Act: -0.0000

Data Index: 1163454 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 6.8690. Min Range: -6.8690

Max Act: 4.0758. Min Act: -0.0000

Data Index: 921562 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.7615. Min Act: -0.0000

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.2942. Min Act: -0.0000

Data Index: 1234317 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.8935. Min Act: -0.0000

Data Index: 68454 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.3844. Min Act: -0.0000

Data Index: 949320 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.4451. Min Act: -0.0000

Data Index: 436984 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 6.8690. Min Range: -6.8690

Max Act: 3.2480. Min Act: -0.0000

Data Index: 194473 (C4 (Web Text))

Max Activating Token Index: 542