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

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

Neuron 3057 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1561599 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1397233 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1587531 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1424247 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1484229 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1368890 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6113. Min Act: -0.0001

Data Index: 10477 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6407. Min Act: -0.0001

Data Index: 1484868 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1551798 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5893. Min Act: -0.0002

Data Index: 336819 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1506068 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6129. Min Act: -0.0001

Data Index: 532477 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1419338 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1379756 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6153. Min Act: -0.0002

Data Index: 1524075 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6038. Min Act: -0.0002

Data Index: 134658 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1657017 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1508842 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1653825 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.8316. Min Range: -0.8316

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1174145 (C4 (Web Text))

Max Activating Token Index: 464