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

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

Neuron 5048 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: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1020094 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1718. Min Act: -0.0000

Data Index: 319574 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1578. Min Act: -0.0000

Data Index: 106448 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1711. Min Act: -0.0000

Data Index: 417618 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1640. Min Act: -0.0000

Data Index: 646956 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1423841 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1647348 (Python Code)

Max Activating Token Index: 888

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1479. Min Act: -0.0000

Data Index: 156620 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1468. Min Act: -0.0000

Data Index: 540343 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1479. Min Act: -0.0000

Data Index: 704767 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1472. Min Act: -0.0000

Data Index: 29146 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1439. Min Act: -0.0001

Data Index: 840061 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1408. Min Act: -0.0000

Data Index: 182409 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1149479 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1450. Min Act: -0.0000

Data Index: 152682 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1432256 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1364. Min Act: -0.0000

Data Index: 281361 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1263. Min Act: -0.0000

Data Index: 178124 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1310. Min Act: -0.0001

Data Index: 91873 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1300. Min Act: -0.0000

Data Index: 293345 (C4 (Web Text))

Max Activating Token Index: 52