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

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

Neuron 3322 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: 0.5528. Min Range: -0.5528

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1225369 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5126. Min Act: -0.0000

Data Index: 771462 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4885. Min Act: -0.0000

Data Index: 245613 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4900. Min Act: -0.0000

Data Index: 588556 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4866. Min Act: -0.0000

Data Index: 783235 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1109334 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4387. Min Act: -0.0000

Data Index: 821574 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4419. Min Act: -0.0000

Data Index: 668046 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4284. Min Act: -0.0000

Data Index: 403355 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1239985 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1340494 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1252143 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1115397 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1059179 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1087154 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1089384 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1250364 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4068. Min Act: -0.0000

Data Index: 587266 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3814. Min Act: -0.0000

Data Index: 702826 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1023933 (C4 (Web Text))

Max Activating Token Index: 432