Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3969 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1563489 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1454023 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1606464 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3376. Min Act: -0.0000

Data Index: 1500563 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.3768. Min Act: -0.0000

Data Index: 298993 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1569542 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1422007 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1645453 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1594447 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1474974 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1514541 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1530784 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1481534 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0527. Min Act: -0.0001

Data Index: 1399676 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1511192 (Python Code)

Max Activating Token Index: 359

Text #15

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0528. Min Act: -0.0000

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1384028 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 1.7534. Min Range: -1.7534

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1573346 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1374809 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 1.7534. Min Range: -1.7534

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1403358 (Python Code)

Max Activating Token Index: 329