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

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

Neuron 2958 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: 1.5339. Min Range: -1.5339

Max Act: 1.4784. Min Act: -0.0001

Data Index: 1427924 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.5339. Min Act: -0.0001

Data Index: 1503648 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2651. Min Act: -0.0001

Data Index: 1575153 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3647. Min Act: -0.0001

Data Index: 1417396 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3243. Min Act: -0.0001

Data Index: 1531058 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2812. Min Act: -0.0001

Data Index: 1536620 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2334. Min Act: -0.0001

Data Index: 1600609 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3242. Min Act: -0.0001

Data Index: 1572818 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2131. Min Act: -0.0001

Data Index: 1451863 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3033. Min Act: -0.0001

Data Index: 1538104 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2717. Min Act: -0.0001

Data Index: 1401963 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2472. Min Act: -0.0001

Data Index: 1480271 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3049. Min Act: -0.0001

Data Index: 1397854 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2273. Min Act: -0.0001

Data Index: 1057976 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3018. Min Act: -0.0001

Data Index: 1380799 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2773. Min Act: -0.0001

Data Index: 1383413 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1110. Min Act: -0.0001

Data Index: 328339 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1835. Min Act: -0.0001

Data Index: 1409145 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1417976 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1341. Min Act: -0.0001

Data Index: 1557079 (Python Code)

Max Activating Token Index: 613