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

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

Neuron 4106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1510212 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2317. Min Act: -0.0001

Data Index: 207564 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0001

Data Index: 834025 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2201. Min Act: -0.0001

Data Index: 218346 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1010160 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2062. Min Act: -0.0001

Data Index: 246961 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1999. Min Act: -0.0001

Data Index: 933324 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2049. Min Act: -0.0001

Data Index: 832708 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2070. Min Act: -0.0001

Data Index: 63326 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2001. Min Act: -0.0001

Data Index: 480389 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1874. Min Act: -0.0001

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1005327 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2027. Min Act: -0.0001

Data Index: 503724 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2031. Min Act: -0.0001

Data Index: 819608 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2088. Min Act: -0.0001

Data Index: 736290 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1900. Min Act: -0.0001

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1972. Min Act: -0.0001

Data Index: 65129 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1968. Min Act: -0.0001

Data Index: 713658 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2080. Min Act: -0.0001

Data Index: 317222 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1927. Min Act: -0.0001

Data Index: 309638 (C4 (Web Text))

Max Activating Token Index: 198