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

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

Neuron 3520 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: 0.6790. Min Range: -0.6790

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1089486 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6392. Min Act: -0.0000

Data Index: 560260 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6578. Min Act: -0.0001

Data Index: 338553 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6116. Min Act: -0.0001

Data Index: 807758 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6152. Min Act: -0.0001

Data Index: 752104 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1060682 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6082. Min Act: -0.0001

Data Index: 617269 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1359230 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5632. Min Act: -0.0000

Data Index: 530943 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5359. Min Act: -0.0000

Data Index: 466063 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5279. Min Act: -0.0001

Data Index: 1285539 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5200. Min Act: -0.0001

Data Index: 1363316 (Python Code)

Max Activating Token Index: 765

Text #12

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5156. Min Act: -0.0001

Data Index: 1625709 (Python Code)

Max Activating Token Index: 970

Text #13

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4940. Min Act: -0.0001

Data Index: 784710 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.5089. Min Act: -0.0001

Data Index: 213633 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1045263 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4675. Min Act: -0.0000

Data Index: 382892 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1627915 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4876. Min Act: -0.0001

Data Index: 1135296 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.6790. Min Range: -0.6790

Max Act: 0.4543. Min Act: -0.0000

Data Index: 78557 (C4 (Web Text))

Max Activating Token Index: 766