Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0463. Min Range: -3.0463

Max Act: 3.0463. Min Act: -0.0000

Data Index: 1076496 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.9954. Min Act: -0.0000

Data Index: 422914 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.6090. Min Act: -0.0000

Data Index: 1102305 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.6778. Min Act: -0.0001

Data Index: 439833 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.5980. Min Act: -0.0001

Data Index: 381596 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.5705. Min Act: -0.0001

Data Index: 1018050 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.6657. Min Act: -0.0000

Data Index: 303713 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.4166. Min Act: -0.0000

Data Index: 1081368 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.3275. Min Act: -0.0000

Data Index: 536097 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.3742. Min Act: -0.0000

Data Index: 747163 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.3311. Min Act: -0.0000

Data Index: 1238978 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.3027. Min Act: -0.0000

Data Index: 1283787 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.2126. Min Act: -0.0001

Data Index: 386744 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.2143. Min Act: -0.0001

Data Index: 1029322 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.1072. Min Act: -0.0000

Data Index: 397189 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.0986. Min Act: -0.0001

Data Index: 712685 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.0825. Min Act: -0.0001

Data Index: 680796 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.2426. Min Act: -0.0000

Data Index: 1212120 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.0289. Min Act: -0.0001

Data Index: 995732 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.0463. Min Range: -3.0463

Max Act: 1.9121. Min Act: -0.0000

Data Index: 114616 (C4 (Web Text))

Max Activating Token Index: 744