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

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

Neuron 4751 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1506590 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1389507 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0680. Min Act: -0.0000

Data Index: 815507 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1558194 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1420851 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0582. Min Act: -0.0001

Data Index: 952832 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0567. Min Act: -0.0000

Data Index: 552987 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0612. Min Act: -0.0001

Data Index: 719678 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0561. Min Act: -0.0001

Data Index: 606160 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0544. Min Act: -0.0000

Data Index: 758049 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1330005 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1101783 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0489. Min Act: -0.0001

Data Index: 276892 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0448. Min Act: -0.0001

Data Index: 508597 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1511559 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0467. Min Act: -0.0001

Data Index: 444097 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0438. Min Act: -0.0000

Data Index: 411807 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1540424 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0443. Min Act: -0.0001

Data Index: 949064 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0457. Min Act: -0.0001

Data Index: 665705 (C4 (Web Text))

Max Activating Token Index: 611