Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2051 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1535478 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1418591 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7442. Min Act: -0.0001

Data Index: 1639538 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1551463 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1543550 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6524. Min Act: -0.0001

Data Index: 1610443 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1407272 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1500457 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1494507 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6366. Min Act: -0.0001

Data Index: 1465457 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1644539 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1366055 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1445887 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1586323 (Python Code)

Max Activating Token Index: 491

Text #14

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1371107 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1643545 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1603973 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7799. Min Act: -0.0001

Data Index: 1364644 (Python Code)

Max Activating Token Index: 797

Text #18

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1423819 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1474173 (Python Code)

Max Activating Token Index: 27