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

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

Neuron 1617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5195. Min Act: -0.0001

Data Index: 1549683 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1421003 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1441000 (Python Code)

Max Activating Token Index: 368

Text #3

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1532583 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1443420 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5795. Min Act: -0.0001

Data Index: 1563615 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1403270 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.6263. Min Act: -0.0001

Data Index: 1425210 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5855. Min Act: -0.0001

Data Index: 1446898 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5473. Min Act: -0.0001

Data Index: 1520959 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1533422 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5039. Min Act: -0.0001

Data Index: 1497980 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1453323 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1452693 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1364612 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4435. Min Act: -0.0001

Data Index: 1361049 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1543129 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1420449 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4554. Min Act: -0.0001

Data Index: 1453569 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 0.6573. Min Range: -0.6573

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1460271 (Python Code)

Max Activating Token Index: 37