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

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

Neuron 229 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.9067. Min Act: -0.0000

Data Index: 542332 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.8049. Min Act: -0.0000

Data Index: 840039 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6913. Min Act: -0.0000

Data Index: 545152 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6559. Min Act: -0.0000

Data Index: 602741 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7044. Min Act: -0.0000

Data Index: 512235 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5982. Min Act: -0.0000

Data Index: 871285 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1285545 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6560. Min Act: -0.0000

Data Index: 338693 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5687. Min Act: -0.0000

Data Index: 551185 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1250500 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5542. Min Act: -0.0000

Data Index: 889719 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5615. Min Act: -0.0000

Data Index: 543712 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6018. Min Act: -0.0000

Data Index: 354065 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5413. Min Act: -0.0000

Data Index: 831262 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1587977 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1104045 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6129. Min Act: -0.0000

Data Index: 499582 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5130. Min Act: -0.0000

Data Index: 944506 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1279884 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1255150 (C4 (Web Text))

Max Activating Token Index: 319