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

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

Neuron 360 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.6101. Min Act: -0.0002

Data Index: 438770 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5850. Min Act: -0.0002

Data Index: 542270 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5766. Min Act: -0.0001

Data Index: 118287 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5697. Min Act: -0.0002

Data Index: 750391 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5695. Min Act: -0.0002

Data Index: 796011 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5572. Min Act: -0.0002

Data Index: 753052 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5569. Min Act: -0.0002

Data Index: 8041 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5537. Min Act: -0.0002

Data Index: 783528 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5485. Min Act: -0.0001

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5466. Min Act: -0.0002

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5450. Min Act: -0.0002

Data Index: 1137438 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5425. Min Act: -0.0002

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5404. Min Act: -0.0002

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5397. Min Act: -0.0002

Data Index: 716727 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5367. Min Act: -0.0002

Data Index: 988799 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5369. Min Act: -0.0001

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5349. Min Act: -0.0002

Data Index: 722003 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5339. Min Act: -0.0001

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5505. Min Act: -0.0002

Data Index: 81649 (C4 (Web Text))

Max Activating Token Index: 583