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

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

Neuron 2136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1291. Min Range: -1.1291

Max Act: 1.1291. Min Act: -0.0000

Data Index: 305789 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.9229. Min Act: -0.0000

Data Index: 675585 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8899. Min Act: -0.0000

Data Index: 604154 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8478. Min Act: -0.0000

Data Index: 707748 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7830. Min Act: -0.0000

Data Index: 373313 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8261. Min Act: -0.0000

Data Index: 473765 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7614. Min Act: -0.0000

Data Index: 430769 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8277. Min Act: -0.0000

Data Index: 620023 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7709. Min Act: -0.0000

Data Index: 552041 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7703. Min Act: -0.0000

Data Index: 909349 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7659. Min Act: -0.0000

Data Index: 887915 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7643. Min Act: -0.0000

Data Index: 156271 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7663. Min Act: -0.0000

Data Index: 755629 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7836. Min Act: -0.0000

Data Index: 195119 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1019378 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7290. Min Act: -0.0000

Data Index: 532603 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1333939 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7415. Min Act: -0.0000

Data Index: 344873 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1298758 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6952. Min Act: -0.0000

Data Index: 495864 (C4 (Web Text))

Max Activating Token Index: 615