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

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

Neuron 757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1098490 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1215675 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0587. Min Act: -0.0001

Data Index: 289941 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0592. Min Act: -0.0001

Data Index: 976519 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1124374 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0555. Min Act: -0.0001

Data Index: 588415 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1041038 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0494. Min Act: -0.0001

Data Index: 150379 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0512. Min Act: -0.0001

Data Index: 43047 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0534. Min Act: -0.0001

Data Index: 656919 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0485. Min Act: -0.0001

Data Index: 227065 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1175078 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1329850 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1070941 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0444. Min Act: -0.0001

Data Index: 378062 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0469. Min Act: -0.0001

Data Index: 41842 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0451. Min Act: -0.0001

Data Index: 952582 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0477. Min Act: -0.0001

Data Index: 180493 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0486. Min Act: -0.0001

Data Index: 742516 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1289102 (C4 (Web Text))

Max Activating Token Index: 428