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

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

Neuron 2933 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: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1431171 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1413786 (Python Code)

Max Activating Token Index: 739

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1546526 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1577934 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1652617 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1559306 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1619606 (Python Code)

Max Activating Token Index: 483

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1425712 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1550010 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1385231 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0837. Min Act: -0.0000

Data Index: 300650 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1463803 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1616259 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1210953 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1395198 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1560900 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1448495 (Python Code)

Max Activating Token Index: 816

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1349892 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1598956 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1607781 (Python Code)

Max Activating Token Index: 398