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

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

Neuron 4107 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.5818. Min Act: -0.0000

Data Index: 1414744 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.5857. Min Act: -0.0000

Data Index: 1397803 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.2875. Min Act: -0.0000

Data Index: 1477713 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.1617. Min Act: -0.0000

Data Index: 1626774 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.0418. Min Act: -0.0000

Data Index: 1411775 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.9580. Min Act: -0.0000

Data Index: 1427451 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 4.5857. Min Range: -4.5857

Max Act: 4.0881. Min Act: -0.0000

Data Index: 1398856 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.9289. Min Act: -0.0000

Data Index: 1443586 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.8302. Min Act: -0.0000

Data Index: 1499665 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.6897. Min Act: -0.0000

Data Index: 1445930 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.6611. Min Act: -0.0000

Data Index: 1632822 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.6990. Min Act: -0.0000

Data Index: 1650193 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.7052. Min Act: -0.0000

Data Index: 1590424 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.6502. Min Act: -0.0000

Data Index: 1467742 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.5928. Min Act: -0.0000

Data Index: 1384544 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.5812. Min Act: -0.0000

Data Index: 1517290 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.5686. Min Act: -0.0000

Data Index: 1382778 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.5375. Min Act: -0.0000

Data Index: 1447148 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.5139. Min Act: -0.0000

Data Index: 1441447 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 4.5857. Min Range: -4.5857

Max Act: 3.2946. Min Act: -0.0000

Data Index: 1489131 (Python Code)

Max Activating Token Index: 1014