Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3068 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1479290 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0555. Min Act: -0.0001

Data Index: 236649 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0001

Data Index: 352402 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0506. Min Act: -0.0001

Data Index: 597383 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1572374 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0495. Min Act: -0.0001

Data Index: 639841 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0490. Min Act: -0.0001

Data Index: 825793 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1005689 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1032366 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1186159 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1464171 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0478. Min Act: -0.0001

Data Index: 405293 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0474. Min Act: -0.0001

Data Index: 184466 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1628042 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0465. Min Act: -0.0001

Data Index: 570236 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1249943 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0453. Min Act: -0.0001

Data Index: 246689 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1209192 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0449. Min Act: -0.0001

Data Index: 347114 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1037408 (C4 (Web Text))

Max Activating Token Index: 264