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

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

Neuron 1808 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1400317 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1586442 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1476616 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1319861 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1197106 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2817. Min Act: 0.0001

Data Index: 761982 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1438347 (Python Code)

Max Activating Token Index: 871

Text #7

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1866. Min Act: -0.0000

Data Index: 205495 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1422. Min Act: -0.0000

Data Index: 171538 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1103. Min Act: -0.0000

Data Index: 248107 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1703. Min Act: -0.0000

Data Index: 568663 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0910. Min Act: -0.0000

Data Index: 231151 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1154. Min Act: -0.0000

Data Index: 994963 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0911. Min Act: -0.0000

Data Index: 707709 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0780. Min Act: -0.0000

Data Index: 19057 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0466. Min Act: -0.0000

Data Index: 997238 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0713. Min Act: -0.0000

Data Index: 728558 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0600. Min Act: -0.0000

Data Index: 50434 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0549. Min Act: -0.0000

Data Index: 633301 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0527. Min Act: -0.0000

Data Index: 212621 (C4 (Web Text))

Max Activating Token Index: 1007