Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1802 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0002

Data Index: 573054 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0506. Min Act: -0.0001

Data Index: 745348 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0510. Min Act: -0.0002

Data Index: 869388 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0506. Min Act: -0.0002

Data Index: 104223 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0491. Min Act: -0.0002

Data Index: 666679 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0493. Min Act: -0.0002

Data Index: 761778 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0493. Min Act: -0.0002

Data Index: 560134 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1347091 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0466. Min Act: -0.0002

Data Index: 422709 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0467. Min Act: -0.0002

Data Index: 2405 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1245929 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0460. Min Act: -0.0002

Data Index: 902368 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1619159 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0438. Min Act: -0.0002

Data Index: 880033 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0454. Min Act: -0.0002

Data Index: 820336 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0456. Min Act: -0.0002

Data Index: 85214 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0427. Min Act: -0.0002

Data Index: 950919 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0463. Min Act: -0.0002

Data Index: 711705 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0450. Min Act: -0.0002

Data Index: 311771 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0445. Min Act: -0.0002

Data Index: 144976 (C4 (Web Text))

Max Activating Token Index: 1018