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

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

Neuron 138 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: 0.8966. Min Range: -0.8966

Max Act: 0.8966. Min Act: -0.0000

Data Index: 27492 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7894. Min Act: -0.0000

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7710. Min Act: -0.0000

Data Index: 157711 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1600024 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7651. Min Act: -0.0000

Data Index: 596689 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1596427 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7387. Min Act: -0.0000

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7337. Min Act: -0.0000

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7362. Min Act: -0.0000

Data Index: 683592 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1018197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7226. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6939. Min Act: -0.0000

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1030959 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1544170 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6768. Min Act: -0.0000

Data Index: 443271 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1091903 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6902. Min Act: -0.0000

Data Index: 919983 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6508. Min Act: -0.0000

Data Index: 542189 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1209200 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7091. Min Act: -0.0000

Data Index: 866412 (C4 (Web Text))

Max Activating Token Index: 72