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

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

Neuron 4308 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: 3.8198. Min Range: -3.8198

Max Act: 3.8198. Min Act: -0.0000

Data Index: 1236142 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.9032. Min Act: -0.0000

Data Index: 917621 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 3.8198. Min Range: -3.8198

Max Act: 3.1075. Min Act: -0.0000

Data Index: 880991 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.9452. Min Act: -0.0000

Data Index: 977843 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.9684. Min Act: -0.0000

Data Index: 80861 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.8042. Min Act: -0.0000

Data Index: 1506168 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.7409. Min Act: -0.0000

Data Index: 116743 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.7111. Min Act: -0.0000

Data Index: 1093800 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.6704. Min Act: -0.0000

Data Index: 1320756 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.3599. Min Act: -0.0000

Data Index: 553253 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.5895. Min Act: -0.0000

Data Index: 672353 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.5707. Min Act: -0.0000

Data Index: 563106 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.3881. Min Act: -0.0000

Data Index: 363077 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.5583. Min Act: -0.0000

Data Index: 1622883 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.2900. Min Act: -0.0000

Data Index: 907664 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.1600. Min Act: -0.0000

Data Index: 339290 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.3393. Min Act: -0.0000

Data Index: 126313 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 3.8198. Min Range: -3.8198

Max Act: 2.1287. Min Act: -0.0000

Data Index: 1220208 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 3.8198. Min Range: -3.8198

Max Act: 1.7877. Min Act: 0.0001

Data Index: 1541040 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 3.8198. Min Range: -3.8198

Max Act: 1.9943. Min Act: -0.0000

Data Index: 856312 (C4 (Web Text))

Max Activating Token Index: 533