Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1925 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.9473. Min Range: -7.9473

Max Act: 7.9473. Min Act: -0.0000

Data Index: 325857 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.6328. Min Act: -0.0000

Data Index: 730096 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.9675. Min Act: -0.0000

Data Index: 1001231 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.4872. Min Act: -0.0000

Data Index: 135586 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.9326. Min Act: -0.0000

Data Index: 997307 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.4598. Min Act: -0.0000

Data Index: 934018 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.2736. Min Act: -0.0000

Data Index: 412263 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.7317. Min Act: -0.0000

Data Index: 480992 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.2170. Min Act: -0.0000

Data Index: 546120 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.7639. Min Act: -0.0000

Data Index: 678940 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.3164. Min Act: -0.0000

Data Index: 1086179 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.2121. Min Act: -0.0000

Data Index: 1275984 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.4039. Min Act: -0.0000

Data Index: 446332 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.8051. Min Act: -0.0000

Data Index: 1107603 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.8097. Min Act: -0.0000

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.4083. Min Act: -0.0000

Data Index: 857513 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.4012. Min Act: -0.0000

Data Index: 843050 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.3796. Min Act: -0.0000

Data Index: 349158 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.5615. Min Act: -0.0000

Data Index: 359908 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 7.9473. Min Range: -7.9473

Max Act: 5.5586. Min Act: -0.0000

Data Index: 596251 (C4 (Web Text))

Max Activating Token Index: 979