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

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

Neuron 1365 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: 4.1326. Min Range: -4.1326

Max Act: 4.0923. Min Act: -0.0001

Data Index: 1597940 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 4.1326. Min Range: -4.1326

Max Act: 4.0704. Min Act: -0.0001

Data Index: 1414402 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 4.1326. Min Range: -4.1326

Max Act: 4.1326. Min Act: -0.0001

Data Index: 1655331 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 4.1326. Min Range: -4.1326

Max Act: 4.1145. Min Act: -0.0001

Data Index: 1542687 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.3552. Min Act: -0.0001

Data Index: 1544028 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.6138. Min Act: -0.0001

Data Index: 1458240 (Python Code)

Max Activating Token Index: 800

Text #6

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.7474. Min Act: -0.0001

Data Index: 1643435 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.5929. Min Act: -0.0001

Data Index: 1593370 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.6787. Min Act: -0.0001

Data Index: 1571268 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.5850. Min Act: -0.0001

Data Index: 1412846 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.2585. Min Act: -0.0001

Data Index: 1416336 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.6499. Min Act: -0.0001

Data Index: 1558618 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.6715. Min Act: -0.0001

Data Index: 1511096 (Python Code)

Max Activating Token Index: 1003

Text #13

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.4406. Min Act: -0.0001

Data Index: 1602216 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.7351. Min Act: -0.0001

Data Index: 1414638 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.2702. Min Act: -0.0001

Data Index: 1586791 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.4189. Min Act: -0.0001

Data Index: 1605432 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.4199. Min Act: -0.0001

Data Index: 1376582 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.5382. Min Act: -0.0001

Data Index: 1513255 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.2471. Min Act: -0.0001

Data Index: 1453286 (Python Code)

Max Activating Token Index: 828