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

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

Neuron 583 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0869. Min Range: -7.0869

Max Act: 7.0869. Min Act: -0.0000

Data Index: 1593624 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.9812. Min Act: -0.0000

Data Index: 1598336 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.8830. Min Act: -0.0000

Data Index: 1531731 (Python Code)

Max Activating Token Index: 410

Text #3

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.5530. Min Act: -0.0000

Data Index: 1406226 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.6694. Min Act: -0.0000

Data Index: 1380913 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.3293. Min Act: -0.0000

Data Index: 1648028 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.7395. Min Act: -0.0000

Data Index: 1478466 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.0765. Min Act: -0.0000

Data Index: 1411495 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.6088. Min Act: -0.0000

Data Index: 1493873 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.9937. Min Act: -0.0000

Data Index: 1426159 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.1395. Min Act: -0.0000

Data Index: 1413480 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.0834. Min Act: -0.0000

Data Index: 1503009 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.2666. Min Act: -0.0000

Data Index: 1498467 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.2826. Min Act: -0.0000

Data Index: 1520974 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 7.0869. Min Range: -7.0869

Max Act: 6.1095. Min Act: -0.0000

Data Index: 1591108 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.7160. Min Act: -0.0000

Data Index: 1462210 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.5870. Min Act: -0.0000

Data Index: 1634160 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.3463. Min Act: -0.0000

Data Index: 1424319 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.7728. Min Act: -0.0000

Data Index: 1410555 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 7.0869. Min Range: -7.0869

Max Act: 5.7370. Min Act: -0.0000

Data Index: 1477234 (Python Code)

Max Activating Token Index: 158