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

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

Neuron 3390 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4038. Min Act: -0.0000

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1301401 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5466. Min Act: -0.0000

Data Index: 292160 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5187. Min Act: -0.0000

Data Index: 789804 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1314201 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5045. Min Act: -0.0000

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5043. Min Act: -0.0000

Data Index: 58958 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1325716 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4856. Min Act: -0.0000

Data Index: 449650 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1315095 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4784. Min Act: -0.0000

Data Index: 264657 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1085426 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4911. Min Act: -0.0000

Data Index: 648540 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4476. Min Act: -0.0000

Data Index: 519702 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4672. Min Act: -0.0000

Data Index: 519831 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4918. Min Act: -0.0000

Data Index: 376348 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1231924 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1271795 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4564. Min Act: -0.0000

Data Index: 173599 (C4 (Web Text))

Max Activating Token Index: 560