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

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

Neuron 3271 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: 1.9964. Min Range: -1.9964

Max Act: 1.9964. Min Act: -0.0000

Data Index: 76762 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.9142. Min Act: -0.0000

Data Index: 253795 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.0043. Min Act: -0.0000

Data Index: 582344 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.9599. Min Act: -0.0000

Data Index: 647492 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.9304. Min Act: -0.0000

Data Index: 558706 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8907. Min Act: -0.0000

Data Index: 776537 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8379. Min Act: -0.0000

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8800. Min Act: -0.0000

Data Index: 727661 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8485. Min Act: -0.0000

Data Index: 915017 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1167216 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8270. Min Act: -0.0000

Data Index: 702070 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8637. Min Act: -0.0000

Data Index: 708747 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8073. Min Act: -0.0000

Data Index: 507581 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.8350. Min Act: -0.0000

Data Index: 847886 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7757. Min Act: -0.0000

Data Index: 91779 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7737. Min Act: -0.0000

Data Index: 744888 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1020440 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7601. Min Act: -0.0000

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7848. Min Act: -0.0000

Data Index: 293935 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.9964. Min Range: -1.9964

Max Act: 0.7094. Min Act: -0.0000

Data Index: 239947 (C4 (Web Text))

Max Activating Token Index: 545