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

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

Neuron 1864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3552. Min Range: -4.3552

Max Act: 4.3552. Min Act: -0.0000

Data Index: 772328 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 4.3552. Min Range: -4.3552

Max Act: 4.2108. Min Act: -0.0000

Data Index: 1198045 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.9051. Min Act: -0.0001

Data Index: 1338005 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.8789. Min Act: -0.0000

Data Index: 905582 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.8719. Min Act: -0.0001

Data Index: 309108 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7082. Min Act: -0.0000

Data Index: 469616 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.8801. Min Act: -0.0000

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.8178. Min Act: -0.0001

Data Index: 1053294 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.9208. Min Act: -0.0000

Data Index: 567207 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7483. Min Act: -0.0000

Data Index: 811198 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7450. Min Act: -0.0001

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7414. Min Act: -0.0001

Data Index: 642662 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.6005. Min Act: -0.0001

Data Index: 438710 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7266. Min Act: -0.0000

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7256. Min Act: -0.0001

Data Index: 942807 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.7197. Min Act: -0.0001

Data Index: 407941 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.5562. Min Act: -0.0000

Data Index: 441033 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.6994. Min Act: -0.0000

Data Index: 687849 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.6893. Min Act: -0.0000

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 4.3552. Min Range: -4.3552

Max Act: 3.6620. Min Act: -0.0000

Data Index: 272784 (C4 (Web Text))

Max Activating Token Index: 155