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

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

Neuron 5490 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1641091 (Python Code)

Max Activating Token Index: 729

Text #1

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1542073 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1647089 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5319. Min Act: -0.0000

Data Index: 82807 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1170492 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5314. Min Act: -0.0000

Data Index: 887231 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1372258 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1508620 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4662. Min Act: -0.0000

Data Index: 396224 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4648. Min Act: -0.0000

Data Index: 919111 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3879. Min Act: -0.0000

Data Index: 753860 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4437. Min Act: -0.0000

Data Index: 329755 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1402506 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4085. Min Act: -0.0000

Data Index: 585198 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4100. Min Act: -0.0000

Data Index: 350568 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1004788 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1367464 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3839. Min Act: -0.0000

Data Index: 784849 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1648846 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1125791 (C4 (Web Text))

Max Activating Token Index: 513