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

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

Neuron 2434 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: 6.4770. Min Range: -6.4770

Max Act: 6.4770. Min Act: -0.0000

Data Index: 1188644 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7960. Min Act: -0.0000

Data Index: 1033728 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.9333. Min Act: -0.0000

Data Index: 800345 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 6.4770. Min Range: -6.4770

Max Act: 6.0682. Min Act: -0.0000

Data Index: 507097 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 6.4770. Min Range: -6.4770

Max Act: 6.0769. Min Act: -0.0000

Data Index: 269770 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.8306. Min Act: -0.0000

Data Index: 1050455 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.9565. Min Act: -0.0000

Data Index: 690417 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.8424. Min Act: -0.0000

Data Index: 1102723 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7747. Min Act: -0.0000

Data Index: 1311732 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7363. Min Act: -0.0000

Data Index: 51581 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.5595. Min Act: -0.0000

Data Index: 742875 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7430. Min Act: -0.0000

Data Index: 619163 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.5365. Min Act: -0.0000

Data Index: 1163072 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.6898. Min Act: -0.0000

Data Index: 1331489 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.6997. Min Act: -0.0000

Data Index: 428208 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.8225. Min Act: -0.0000

Data Index: 467208 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.6269. Min Act: -0.0000

Data Index: 432310 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.3718. Min Act: -0.0000

Data Index: 1235878 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7461. Min Act: -0.0000

Data Index: 114268 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 6.4770. Min Range: -6.4770

Max Act: 5.7174. Min Act: -0.0000

Data Index: 574649 (C4 (Web Text))

Max Activating Token Index: 600