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

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

Neuron 987 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: 0.5236. Min Range: -0.5236

Max Act: 0.5236. Min Act: -0.0000

Data Index: 556623 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.5126. Min Act: -0.0000

Data Index: 703444 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.5095. Min Act: -0.0000

Data Index: 397380 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1161371 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4447. Min Act: -0.0000

Data Index: 573784 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4778. Min Act: -0.0000

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4306. Min Act: -0.0000

Data Index: 956735 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4581. Min Act: -0.0000

Data Index: 784090 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4583. Min Act: -0.0000

Data Index: 800590 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4662. Min Act: -0.0000

Data Index: 747765 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4211. Min Act: -0.0000

Data Index: 467618 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4520. Min Act: -0.0000

Data Index: 206898 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4356. Min Act: -0.0000

Data Index: 396379 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4128. Min Act: -0.0000

Data Index: 302757 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4433. Min Act: -0.0000

Data Index: 934110 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1124066 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.3955. Min Act: -0.0000

Data Index: 268447 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4048. Min Act: -0.0000

Data Index: 959196 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1224584 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.5236. Min Range: -0.5236

Max Act: 0.4037. Min Act: -0.0000

Data Index: 862607 (C4 (Web Text))

Max Activating Token Index: 727