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

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

Neuron 2055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1366302 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1639002 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1477868 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1466020 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1400998 (Python Code)

Max Activating Token Index: 434

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1438953 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1496505 (Python Code)

Max Activating Token Index: 589

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1558876 (Python Code)

Max Activating Token Index: 243

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1516500 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6442. Min Act: -0.0000

Data Index: 627612 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1625250 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1422322 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1427361 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1421997 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1525333 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1528200 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1478143 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1429923 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1644981 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5047. Min Act: -0.0000

Data Index: 77849 (C4 (Web Text))

Max Activating Token Index: 1023