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

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

Neuron 2625 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: 1.2910. Min Range: -1.2910

Max Act: 1.2910. Min Act: -0.0001

Data Index: 1591925 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1525523 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1885. Min Act: -0.0001

Data Index: 1643924 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0956. Min Act: -0.0001

Data Index: 1451942 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1623912 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0455. Min Act: -0.0001

Data Index: 1642648 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1552344 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0471. Min Act: -0.0001

Data Index: 1483912 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9266. Min Act: -0.0001

Data Index: 1485963 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9485. Min Act: -0.0001

Data Index: 1583183 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9772. Min Act: -0.0001

Data Index: 1593410 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9488. Min Act: -0.0001

Data Index: 1567573 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9451. Min Act: -0.0001

Data Index: 1483277 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0632. Min Act: -0.0001

Data Index: 1423442 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1651718 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1375450 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1579721 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9425. Min Act: -0.0001

Data Index: 1494141 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1542421 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9693. Min Act: -0.0001

Data Index: 1540436 (Python Code)

Max Activating Token Index: 346