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

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

Neuron 634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1432669 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4623. Min Act: -0.0001

Data Index: 1517536 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1383044 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1476789 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.5318. Min Act: -0.0001

Data Index: 1375742 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.6381. Min Act: -0.0000

Data Index: 1520997 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4326. Min Act: -0.0001

Data Index: 1622273 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.5142. Min Act: -0.0001

Data Index: 1488387 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1505823 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3213. Min Act: -0.0001

Data Index: 1626123 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3971. Min Act: -0.0001

Data Index: 1458326 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.2598. Min Act: -0.0001

Data Index: 1442811 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3289. Min Act: -0.0001

Data Index: 1525911 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1427514 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1641375 (Python Code)

Max Activating Token Index: 217

Text #15

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1418999 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4017. Min Act: -0.0000

Data Index: 1449910 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4270. Min Act: -0.0001

Data Index: 1518650 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1593428 (Python Code)

Max Activating Token Index: 432

Text #19

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1385684 (Python Code)

Max Activating Token Index: 228