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

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

Neuron 1064 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: 0.0544. Min Range: -0.0544

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1580629 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0258. Min Act: -0.0000

Data Index: 1616811 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0540. Min Act: -0.0000

Data Index: 375727 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1652935 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1593387 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0520. Min Act: -0.0000

Data Index: 476703 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1379127 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0380. Min Act: -0.0000

Data Index: 910984 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1555459 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0000

Data Index: 781755 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1200087 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1611023 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0345. Min Act: -0.0000

Data Index: 487032 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1478392 (Python Code)

Max Activating Token Index: 969

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0428. Min Act: -0.0000

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1312208 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0418. Min Act: -0.0000

Data Index: 21745 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1624582 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1012511 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0378. Min Act: -0.0000

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 531