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

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

Neuron 1510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1066816 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6553. Min Act: -0.0001

Data Index: 375562 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6764. Min Act: -0.0001

Data Index: 452378 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6545. Min Act: -0.0001

Data Index: 86658 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6074. Min Act: -0.0001

Data Index: 1017848 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6215. Min Act: -0.0001

Data Index: 671205 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6126. Min Act: -0.0001

Data Index: 812625 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6040. Min Act: -0.0001

Data Index: 199302 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5346. Min Act: -0.0001

Data Index: 905251 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1187225 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5468. Min Act: -0.0001

Data Index: 75315 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5346. Min Act: -0.0001

Data Index: 1074632 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5285. Min Act: -0.0001

Data Index: 198508 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5173. Min Act: -0.0001

Data Index: 274487 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5806. Min Act: -0.0001

Data Index: 146528 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5755. Min Act: -0.0001

Data Index: 321923 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5337. Min Act: -0.0001

Data Index: 585736 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4510. Min Act: -0.0001

Data Index: 295253 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5599. Min Act: -0.0001

Data Index: 528657 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5860. Min Act: -0.0001

Data Index: 1292501 (C4 (Web Text))

Max Activating Token Index: 482