Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1744 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9786. Min Act: -0.0002

Data Index: 586815 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9609. Min Act: -0.0002

Data Index: 815428 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9261. Min Act: -0.0002

Data Index: 450480 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9521. Min Act: -0.0002

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9749. Min Act: -0.0003

Data Index: 1338719 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9238. Min Act: -0.0002

Data Index: 694606 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9393. Min Act: -0.0002

Data Index: 427571 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8966. Min Act: -0.0002

Data Index: 930712 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8885. Min Act: -0.0002

Data Index: 216967 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8784. Min Act: -0.0003

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8615. Min Act: -0.0003

Data Index: 227935 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8614. Min Act: -0.0002

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8597. Min Act: -0.0002

Data Index: 1314535 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8501. Min Act: -0.0002

Data Index: 310120 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8496. Min Act: -0.0003

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8741. Min Act: -0.0002

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8365. Min Act: -0.0003

Data Index: 1083226 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8292. Min Act: -0.0002

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8292. Min Act: -0.0002

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8275. Min Act: -0.0003

Data Index: 640658 (C4 (Web Text))

Max Activating Token Index: 25