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

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

Neuron 1022 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.9772. Min Act: -0.0000

Data Index: 647562 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 2.0555. Min Range: -2.0555

Max Act: 2.0555. Min Act: -0.0000

Data Index: 147664 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.6535. Min Act: -0.0000

Data Index: 713554 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.8132. Min Act: -0.0000

Data Index: 650162 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.6298. Min Act: -0.0000

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.4511. Min Act: -0.0000

Data Index: 1093914 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.5182. Min Act: -0.0000

Data Index: 1052743 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.5934. Min Act: -0.0000

Data Index: 1096614 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.5976. Min Act: -0.0000

Data Index: 710711 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1365138 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.4279. Min Act: -0.0000

Data Index: 940703 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.4840. Min Act: -0.0000

Data Index: 781809 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.4317. Min Act: -0.0000

Data Index: 2788 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.4219. Min Act: -0.0000

Data Index: 369910 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1083501 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.3876. Min Act: -0.0000

Data Index: 969359 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1023826 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.3084. Min Act: -0.0000

Data Index: 127883 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.5482. Min Act: -0.0000

Data Index: 785331 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.0555. Min Range: -2.0555

Max Act: 1.3011. Min Act: -0.0000

Data Index: 247500 (C4 (Web Text))

Max Activating Token Index: 293