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

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

Neuron 950 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0514. Min Range: -1.0514

Max Act: 1.0514. Min Act: -0.0000

Data Index: 91977 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9732. Min Act: -0.0000

Data Index: 865517 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9516. Min Act: -0.0000

Data Index: 369400 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1325010 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8733. Min Act: -0.0000

Data Index: 922504 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8433. Min Act: -0.0000

Data Index: 95758 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8430. Min Act: -0.0000

Data Index: 722892 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8654. Min Act: -0.0000

Data Index: 492520 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7749. Min Act: -0.0000

Data Index: 302565 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7679. Min Act: -0.0000

Data Index: 245056 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7571. Min Act: -0.0000

Data Index: 34239 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1003169 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7747. Min Act: -0.0000

Data Index: 937195 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7663. Min Act: -0.0000

Data Index: 878882 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7657. Min Act: -0.0000

Data Index: 637478 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.8117. Min Act: -0.0000

Data Index: 702776 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7415. Min Act: -0.0000

Data Index: 962759 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1160023 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7479. Min Act: -0.0000

Data Index: 438000 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.0514. Min Range: -1.0514

Max Act: 0.7274. Min Act: -0.0000

Data Index: 496781 (C4 (Web Text))

Max Activating Token Index: 843