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

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

Neuron 1446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.3592. Min Act: -0.0000

Data Index: 201761 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1211788 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.3119. Min Act: -0.0000

Data Index: 18489 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1609086 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1405660 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1306954 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2955. Min Act: -0.0000

Data Index: 207773 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1523436 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1289111 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1595849 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1491885 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2683. Min Act: -0.0000

Data Index: 341185 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1079632 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2616. Min Act: -0.0000

Data Index: 907891 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1446785 (Python Code)

Max Activating Token Index: 529

Text #15

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2524. Min Act: -0.0000

Data Index: 121515 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2489. Min Act: -0.0000

Data Index: 861823 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2443. Min Act: -0.0000

Data Index: 436958 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2429. Min Act: -0.0000

Data Index: 549999 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.3592. Min Range: -0.3592

Max Act: 0.2203. Min Act: -0.0000

Data Index: 613045 (C4 (Web Text))

Max Activating Token Index: 636