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

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

Neuron 3468 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1514. Min Range: -2.1514

Max Act: 2.1514. Min Act: -0.0000

Data Index: 1094633 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.7450. Min Act: 0.0000

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1445373 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.6523. Min Act: -0.0000

Data Index: 1543366 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1281633 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.4305. Min Act: -0.0000

Data Index: 216555 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3240. Min Act: -0.0000

Data Index: 702892 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3977. Min Act: 0.0003

Data Index: 1220487 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1312335 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1549731 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3619. Min Act: 0.0003

Data Index: 326668 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1189114 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1064693 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3183. Min Act: -0.0000

Data Index: 22083 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.2364. Min Act: -0.0000

Data Index: 497711 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3127. Min Act: 0.0000

Data Index: 1448827 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.3811. Min Act: -0.0000

Data Index: 595153 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1399908 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1394997 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.1514. Min Range: -2.1514

Max Act: 1.2707. Min Act: -0.0000

Data Index: 428419 (C4 (Web Text))

Max Activating Token Index: 860