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

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

Neuron 3085 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: 4.2073. Min Range: -4.2073

Max Act: 4.0843. Min Act: -0.0000

Data Index: 614642 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 4.2073. Min Range: -4.2073

Max Act: 4.0425. Min Act: -0.0000

Data Index: 864621 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 4.2073. Min Range: -4.2073

Max Act: 4.0786. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 4.2073. Min Range: -4.2073

Max Act: 4.0479. Min Act: -0.0000

Data Index: 1012541 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.6230. Min Act: -0.0000

Data Index: 160195 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.9404. Min Act: -0.0000

Data Index: 927982 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 4.2073. Min Range: -4.2073

Max Act: 4.2073. Min Act: -0.0000

Data Index: 824335 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.5489. Min Act: -0.0000

Data Index: 1242488 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.3623. Min Act: -0.0000

Data Index: 1236939 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 4.2073. Min Range: -4.2073

Max Act: 2.8666. Min Act: -0.0000

Data Index: 256149 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.4739. Min Act: -0.0000

Data Index: 240784 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.2887. Min Act: -0.0000

Data Index: 1071091 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.3912. Min Act: -0.0000

Data Index: 554873 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.5440. Min Act: -0.0000

Data Index: 1045923 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.5681. Min Act: -0.0000

Data Index: 44587 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.4958. Min Act: -0.0000

Data Index: 180844 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.4562. Min Act: -0.0000

Data Index: 668491 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.2900. Min Act: -0.0000

Data Index: 665701 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.4139. Min Act: -0.0000

Data Index: 1241863 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 4.2073. Min Range: -4.2073

Max Act: 3.1764. Min Act: -0.0000

Data Index: 709999 (C4 (Web Text))

Max Activating Token Index: 978