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

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

Neuron 2193 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0179. Min Range: -4.0179

Max Act: 4.0179. Min Act: -0.0000

Data Index: 963201 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 4.0179. Min Range: -4.0179

Max Act: 3.1238. Min Act: -0.0000

Data Index: 949895 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.5824. Min Act: -0.0000

Data Index: 902393 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1332091 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.3897. Min Act: -0.0000

Data Index: 848748 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.1353. Min Act: -0.0000

Data Index: 379865 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.1971. Min Act: -0.0000

Data Index: 392405 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.2595. Min Act: -0.0000

Data Index: 480359 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1254093 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.2014. Min Act: -0.0000

Data Index: 302782 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1131937 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.0567. Min Act: -0.0000

Data Index: 761937 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.9570. Min Act: -0.0000

Data Index: 428076 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 4.0179. Min Range: -4.0179

Max Act: 2.1515. Min Act: -0.0000

Data Index: 1370695 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.8596. Min Act: -0.0000

Data Index: 478221 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.9476. Min Act: -0.0000

Data Index: 222402 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.9110. Min Act: -0.0000

Data Index: 181079 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.9778. Min Act: -0.0000

Data Index: 178955 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.7395. Min Act: -0.0000

Data Index: 593453 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 4.0179. Min Range: -4.0179

Max Act: 1.7337. Min Act: -0.0000

Data Index: 177982 (C4 (Web Text))

Max Activating Token Index: 308