Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2428 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1646839 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1654112 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1474891 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1593532 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1640206 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0463. Min Act: -0.0001

Data Index: 747680 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1397316 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0440. Min Act: -0.0001

Data Index: 757554 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1127890 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1002016 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0445. Min Act: -0.0001

Data Index: 435165 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0446. Min Act: 0.0000

Data Index: 1523668 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1441899 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0439. Min Act: -0.0001

Data Index: 156087 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1049328 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0426. Min Act: -0.0001

Data Index: 985042 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1632209 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0399. Min Act: 0.0000

Data Index: 1180297 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0418. Min Act: 0.0000

Data Index: 200643 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0420. Min Act: -0.0001

Data Index: 269955 (C4 (Web Text))

Max Activating Token Index: 909