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

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

Neuron 1613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1206231 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1123171 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.9123. Min Act: -0.0000

Data Index: 248604 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.8296. Min Act: -0.0000

Data Index: 576033 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1335256 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1162181 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6812. Min Act: -0.0000

Data Index: 374121 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1333209 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1278958 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6940. Min Act: -0.0000

Data Index: 626611 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6420. Min Act: -0.0000

Data Index: 866584 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6699. Min Act: -0.0000

Data Index: 175666 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6606. Min Act: -0.0000

Data Index: 36471 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1162581 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1064087 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6585. Min Act: -0.0000

Data Index: 816203 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6047. Min Act: -0.0000

Data Index: 669217 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6766. Min Act: -0.0000

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.5866. Min Act: -0.0000

Data Index: 18683 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6153. Min Act: -0.0000

Data Index: 814079 (C4 (Web Text))

Max Activating Token Index: 702