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

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

Neuron 2078 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.6674. Min Act: -0.0002

Data Index: 1406178 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.6507. Min Act: -0.0002

Data Index: 1481762 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.6202. Min Act: -0.0002

Data Index: 1370904 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5910. Min Act: -0.0002

Data Index: 1446262 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5487. Min Act: -0.0002

Data Index: 1589493 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.6053. Min Act: -0.0002

Data Index: 1504672 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5553. Min Act: -0.0002

Data Index: 1391909 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5093. Min Act: -0.0002

Data Index: 1524541 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5165. Min Act: -0.0002

Data Index: 1407110 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4955. Min Act: -0.0002

Data Index: 1571213 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4826. Min Act: -0.0002

Data Index: 1374031 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4626. Min Act: -0.0002

Data Index: 1593186 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4806. Min Act: -0.0002

Data Index: 1484694 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4677. Min Act: -0.0002

Data Index: 1552437 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4336. Min Act: -0.0002

Data Index: 1465156 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4387. Min Act: -0.0002

Data Index: 1599189 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4352. Min Act: -0.0002

Data Index: 1473518 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4421. Min Act: -0.0002

Data Index: 1592856 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4378. Min Act: -0.0002

Data Index: 1578618 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4355. Min Act: -0.0002

Data Index: 1547877 (Python Code)

Max Activating Token Index: 358