Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5130 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.8793. Min Act: -0.0001

Data Index: 467461 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.8558. Min Act: -0.0001

Data Index: 1047609 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.8339. Min Act: -0.0001

Data Index: 97790 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7869. Min Act: -0.0001

Data Index: 110255 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7966. Min Act: -0.0001

Data Index: 669644 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7819. Min Act: -0.0001

Data Index: 59057 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.8026. Min Act: -0.0001

Data Index: 867659 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.8032. Min Act: -0.0001

Data Index: 81068 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7175. Min Act: -0.0001

Data Index: 413553 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7433. Min Act: -0.0001

Data Index: 728390 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1599388 (Python Code)

Max Activating Token Index: 347

Text #11

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7283. Min Act: -0.0001

Data Index: 1176438 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7536. Min Act: -0.0001

Data Index: 891124 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7243. Min Act: -0.0001

Data Index: 626321 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.6734. Min Act: -0.0001

Data Index: 1249619 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7053. Min Act: -0.0001

Data Index: 183212 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.7400. Min Act: -0.0001

Data Index: 99562 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.6679. Min Act: -0.0001

Data Index: 1230271 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1381666 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 0.8793. Min Range: -0.8793

Max Act: 0.6453. Min Act: -0.0001

Data Index: 449810 (C4 (Web Text))

Max Activating Token Index: 506