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

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

Neuron 3463 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0002

Data Index: 261177 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0621. Min Act: -0.0002

Data Index: 100911 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0581. Min Act: -0.0002

Data Index: 350894 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1081807 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0542. Min Act: -0.0002

Data Index: 950567 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1229036 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0551. Min Act: -0.0002

Data Index: 343433 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0533. Min Act: -0.0002

Data Index: 334351 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0498. Min Act: -0.0002

Data Index: 52309 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1030771 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0469. Min Act: -0.0002

Data Index: 360313 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0458. Min Act: -0.0002

Data Index: 949833 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1041663 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1030235 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0442. Min Act: -0.0002

Data Index: 23586 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1328072 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0456. Min Act: -0.0002

Data Index: 449174 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0445. Min Act: -0.0002

Data Index: 157097 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0454. Min Act: -0.0002

Data Index: 188790 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0445. Min Act: -0.0002

Data Index: 487518 (C4 (Web Text))

Max Activating Token Index: 631