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

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

Neuron 2319 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1458245 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1408314 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1542666 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1426039 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1514528 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1656856 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1404119 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1596654 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1435069 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1561276 (Python Code)

Max Activating Token Index: 260

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1556244 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1514829 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1559125 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1550658 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1373749 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1607027 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2588. Min Act: -0.0001

Data Index: 1436661 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1367225 (Python Code)

Max Activating Token Index: 333

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1563793 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1488778 (Python Code)

Max Activating Token Index: 743