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

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

Neuron 5480 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.6249. Min Act: -0.0000

Data Index: 819715 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.4899. Min Act: -0.0000

Data Index: 386394 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.4141. Min Act: -0.0000

Data Index: 345142 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.4646. Min Act: -0.0000

Data Index: 1287956 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1262442 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.3229. Min Act: -0.0000

Data Index: 770734 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.3239. Min Act: -0.0000

Data Index: 555712 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2808. Min Act: -0.0000

Data Index: 46937 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2002. Min Act: -0.0000

Data Index: 728638 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2716. Min Act: -0.0001

Data Index: 389802 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2546. Min Act: -0.0000

Data Index: 349320 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.1829. Min Act: -0.0000

Data Index: 504985 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2638. Min Act: -0.0000

Data Index: 915863 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.1497. Min Act: -0.0000

Data Index: 755105 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2322. Min Act: -0.0000

Data Index: 337617 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.3064. Min Act: -0.0000

Data Index: 889092 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2217. Min Act: -0.0000

Data Index: 550705 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.2283. Min Act: -0.0000

Data Index: 478599 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1247686 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.6249. Min Range: -1.6249

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1239758 (C4 (Web Text))

Max Activating Token Index: 51