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

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

Neuron 546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.3349. Min Act: -0.0000

Data Index: 690319 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.1896. Min Act: -0.0000

Data Index: 1030036 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.1715. Min Act: -0.0000

Data Index: 304342 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.1442. Min Act: -0.0000

Data Index: 621899 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.9434. Min Act: -0.0000

Data Index: 798805 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.8092. Min Act: -0.0000

Data Index: 592070 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.9793. Min Act: -0.0000

Data Index: 912100 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.9469. Min Act: -0.0000

Data Index: 437875 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.1156. Min Act: -0.0000

Data Index: 1092088 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 4.3349. Min Range: -4.3349

Max Act: 4.1054. Min Act: -0.0000

Data Index: 490549 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.7202. Min Act: -0.0000

Data Index: 609466 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.5142. Min Act: -0.0000

Data Index: 796622 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.5218. Min Act: -0.0000

Data Index: 785427 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.8025. Min Act: -0.0000

Data Index: 839849 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.4853. Min Act: -0.0000

Data Index: 463250 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.7852. Min Act: -0.0000

Data Index: 837270 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.5876. Min Act: -0.0000

Data Index: 493987 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.7469. Min Act: -0.0000

Data Index: 615084 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.7351. Min Act: -0.0000

Data Index: 1264967 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 4.3349. Min Range: -4.3349

Max Act: 3.7273. Min Act: -0.0000

Data Index: 949692 (C4 (Web Text))

Max Activating Token Index: 623