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

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

Neuron 2419 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1572. Min Act: -0.0002

Data Index: 438376 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1430. Min Act: -0.0002

Data Index: 460956 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1639177 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1319643 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1446. Min Act: -0.0002

Data Index: 746932 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1273607 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1221538 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1648696 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1487555 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1328. Min Act: -0.0002

Data Index: 193587 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1186077 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1247. Min Act: -0.0002

Data Index: 739160 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1265. Min Act: -0.0002

Data Index: 540436 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1068223 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1032801 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1249. Min Act: -0.0002

Data Index: 303088 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1261. Min Act: -0.0002

Data Index: 509104 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1474837 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1218. Min Act: -0.0002

Data Index: 698543 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1223. Min Act: -0.0002

Data Index: 774846 (C4 (Web Text))

Max Activating Token Index: 206