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

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

Neuron 1941 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1067602 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1103940 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1568. Min Act: -0.0000

Data Index: 718718 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0735. Min Act: -0.0000

Data Index: 895130 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1263741 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0800. Min Act: -0.0000

Data Index: 618276 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.1074. Min Act: -0.0000

Data Index: 977677 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.2143. Min Act: -0.0000

Data Index: 174362 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0653. Min Act: -0.0000

Data Index: 218554 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.9593. Min Act: -0.0000

Data Index: 814625 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0544. Min Act: -0.0000

Data Index: 430751 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1124194 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.8958. Min Act: -0.0000

Data Index: 74784 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1193785 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.5369. Min Range: -1.5369

Max Act: 1.0324. Min Act: -0.0000

Data Index: 823780 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.9860. Min Act: -0.0000

Data Index: 431144 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.8635. Min Act: -0.0000

Data Index: 254618 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.8674. Min Act: -0.0000

Data Index: 691426 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.5369. Min Range: -1.5369

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1312005 (C4 (Web Text))

Max Activating Token Index: 377