Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.9009. Min Act: -0.0001

Data Index: 1379997 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7730. Min Act: -0.0001

Data Index: 1606172 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7651. Min Act: -0.0001

Data Index: 290126 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1598384 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6563. Min Act: -0.0001

Data Index: 1466240 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1585476 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5971. Min Act: -0.0001

Data Index: 1587230 (Python Code)

Max Activating Token Index: 403

Text #7

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1331887 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5916. Min Act: -0.0001

Data Index: 351776 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5185. Min Act: -0.0001

Data Index: 234343 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1436715 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1515201 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5187. Min Act: -0.0001

Data Index: 1370319 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5319. Min Act: -0.0001

Data Index: 394502 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5226. Min Act: -0.0001

Data Index: 1531489 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.4751. Min Act: -0.0001

Data Index: 91597 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1163024 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.4822. Min Act: -0.0001

Data Index: 204098 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1448075 (Python Code)

Max Activating Token Index: 775

Text #19

Max Range: 0.9009. Min Range: -0.9009

Max Act: 0.4550. Min Act: -0.0001

Data Index: 1482487 (Python Code)

Max Activating Token Index: 225