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

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

Neuron 2507 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.7634. Min Act: -0.0000

Data Index: 1411255 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1362856 (Python Code)

Max Activating Token Index: 396

Text #2

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3933. Min Act: -0.0000

Data Index: 1588415 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1464857 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1649213 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1496738 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1377201 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1481163 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1577365 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1381205 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2741. Min Act: -0.0000

Data Index: 1572351 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1404613 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1001323 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1374972 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2312. Min Act: -0.0000

Data Index: 555573 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1526662 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1371071 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1363429 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1418794 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 1.7634. Min Range: -1.7634

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1473070 (Python Code)

Max Activating Token Index: 43