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

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

Neuron 4078 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1016309 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1537541 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1650886 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1259. Min Act: -0.0002

Data Index: 404224 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1261. Min Act: -0.0002

Data Index: 803512 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1220. Min Act: -0.0002

Data Index: 849444 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1119. Min Act: -0.0002

Data Index: 21599 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1282989 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1266511 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1065. Min Act: -0.0002

Data Index: 405357 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1041669 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1054. Min Act: -0.0002

Data Index: 927821 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1009. Min Act: -0.0002

Data Index: 64329 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1102566 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1639062 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0995. Min Act: -0.0002

Data Index: 77933 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1034. Min Act: -0.0002

Data Index: 805644 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1109836 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1015. Min Act: -0.0002

Data Index: 608369 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1014. Min Act: -0.0002

Data Index: 849689 (C4 (Web Text))

Max Activating Token Index: 526