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

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

Neuron 2204 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1616498 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1505770 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1370821 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1478476 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1399867 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1485291 (Python Code)

Max Activating Token Index: 885

Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1434577 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2912. Min Act: -0.0001

Data Index: 1506740 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2977. Min Act: -0.0001

Data Index: 1585136 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1639315 (Python Code)

Max Activating Token Index: 267

Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1573371 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1586786 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1654352 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1557458 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1563700 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1468584 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2863. Min Act: -0.0001

Data Index: 1654551 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2601. Min Act: -0.0001

Data Index: 1426907 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1655785 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1616152 (Python Code)

Max Activating Token Index: 518