Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3889 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0695. Min Act: -0.0000

Data Index: 923645 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9124. Min Act: -0.0000

Data Index: 292470 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8601. Min Act: -0.0000

Data Index: 439886 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8529. Min Act: -0.0000

Data Index: 947055 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1385238 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1640025 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8709. Min Act: -0.0000

Data Index: 381758 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7319. Min Act: -0.0000

Data Index: 922395 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7845. Min Act: -0.0000

Data Index: 914301 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8283. Min Act: -0.0000

Data Index: 900193 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1586399 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8137. Min Act: -0.0000

Data Index: 975109 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7908. Min Act: -0.0000

Data Index: 583623 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1159170 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7552. Min Act: -0.0000

Data Index: 752765 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7578. Min Act: -0.0000

Data Index: 278082 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7127. Min Act: -0.0000

Data Index: 390204 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1443451 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1170961 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.5860. Min Act: -0.0000

Data Index: 717361 (C4 (Web Text))

Max Activating Token Index: 669