Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7287. Min Act: -0.0001

Data Index: 1571553 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6118. Min Act: -0.0001

Data Index: 1383830 (Python Code)

Max Activating Token Index: 428

Text #2

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5445. Min Act: -0.0001

Data Index: 1369757 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5451. Min Act: -0.0001

Data Index: 1496474 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1652361 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5308. Min Act: -0.0001

Data Index: 1542202 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1408634 (Python Code)

Max Activating Token Index: 863

Text #7

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5429. Min Act: -0.0001

Data Index: 1597500 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4700. Min Act: -0.0001

Data Index: 1541415 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1374886 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4738. Min Act: -0.0001

Data Index: 1382541 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1534246 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1430820 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4657. Min Act: -0.0001

Data Index: 1470508 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1613256 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1631581 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.5118. Min Act: -0.0001

Data Index: 1582559 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4713. Min Act: -0.0001

Data Index: 1378383 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4392. Min Act: -0.0001

Data Index: 1643946 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1650678 (Python Code)

Max Activating Token Index: 958