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

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

Neuron 3320 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.9975. Min Act: -0.0000

Data Index: 1026196 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.3705. Min Act: -0.0000

Data Index: 819376 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.3569. Min Act: -0.0000

Data Index: 894718 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.1993. Min Act: -0.0000

Data Index: 452795 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.1002. Min Act: -0.0000

Data Index: 1544125 (Python Code)

Max Activating Token Index: 603

Text #5

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.2848. Min Act: -0.0000

Data Index: 691650 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.9894. Min Act: -0.0000

Data Index: 1207627 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.0855. Min Act: 0.0001

Data Index: 636771 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.9975. Min Range: -2.9975

Max Act: 2.0596. Min Act: -0.0000

Data Index: 24388 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.8313. Min Act: -0.0000

Data Index: 801506 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.7825. Min Act: -0.0000

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.7691. Min Act: -0.0000

Data Index: 126000 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.8505. Min Act: -0.0000

Data Index: 1092185 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.6212. Min Act: -0.0000

Data Index: 1034607 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.6826. Min Act: 0.0001

Data Index: 1115855 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.5875. Min Act: -0.0000

Data Index: 916011 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.7791. Min Act: -0.0000

Data Index: 790114 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.5684. Min Act: -0.0000

Data Index: 579349 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.6535. Min Act: -0.0000

Data Index: 1221115 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.9975. Min Range: -2.9975

Max Act: 1.7203. Min Act: -0.0000

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 906