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

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

Neuron 684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9501. Min Act: -0.0000

Data Index: 787261 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1151306 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9042. Min Act: -0.0000

Data Index: 57404 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9019. Min Act: -0.0000

Data Index: 577758 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1350072 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8539. Min Act: -0.0000

Data Index: 883322 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8536. Min Act: -0.0000

Data Index: 132216 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1198922 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7976. Min Act: -0.0000

Data Index: 408045 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8224. Min Act: -0.0001

Data Index: 829765 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8424. Min Act: -0.0000

Data Index: 767369 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7911. Min Act: -0.0000

Data Index: 874280 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1250999 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7861. Min Act: -0.0000

Data Index: 65219 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1287871 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7477. Min Act: -0.0000

Data Index: 566119 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7663. Min Act: -0.0000

Data Index: 256441 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7239. Min Act: -0.0000

Data Index: 641062 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1218549 (C4 (Web Text))

Max Activating Token Index: 987