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

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

Neuron 866 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: 2.4626. Min Range: -2.4626

Max Act: 2.4626. Min Act: -0.0000

Data Index: 838082 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 2.4626. Min Range: -2.4626

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1206199 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 2.4626. Min Range: -2.4626

Max Act: 2.1395. Min Act: -0.0000

Data Index: 265774 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.8886. Min Act: -0.0000

Data Index: 64410 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.9218. Min Act: -0.0000

Data Index: 552954 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7864. Min Act: -0.0000

Data Index: 919686 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.8789. Min Act: -0.0000

Data Index: 997152 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.8708. Min Act: -0.0000

Data Index: 94997 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7573. Min Act: -0.0000

Data Index: 1254959 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.8587. Min Act: -0.0000

Data Index: 234671 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7813. Min Act: -0.0000

Data Index: 512056 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.8923. Min Act: -0.0000

Data Index: 1305117 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7748. Min Act: -0.0000

Data Index: 507529 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1252085 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7113. Min Act: -0.0000

Data Index: 1242121 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.6407. Min Act: -0.0000

Data Index: 516424 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.7338. Min Act: -0.0000

Data Index: 986766 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.6289. Min Act: -0.0000

Data Index: 377147 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.6593. Min Act: -0.0000

Data Index: 724600 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 2.4626. Min Range: -2.4626

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1036472 (C4 (Web Text))

Max Activating Token Index: 209