Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3292 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1437852 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1605004 (Python Code)

Max Activating Token Index: 737

Text #2

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2931. Min Act: -0.0001

Data Index: 1551300 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2572. Min Act: -0.0001

Data Index: 1606681 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1616340 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1505437 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1407893 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1538372 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1397524 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1474354 (Python Code)

Max Activating Token Index: 740

Text #10

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1412744 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1436035 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2587. Min Act: -0.0001

Data Index: 1532025 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1580547 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2636. Min Act: -0.0001

Data Index: 1465245 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1430820 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1411087 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1593023 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1472826 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1460237 (Python Code)

Max Activating Token Index: 784