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

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

Neuron 2905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.5098. Min Act: -0.0001

Data Index: 1016067 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.5879. Min Act: -0.0001

Data Index: 673780 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.5459. Min Act: -0.0001

Data Index: 238926 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4517. Min Act: -0.0001

Data Index: 257621 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4821. Min Act: -0.0001

Data Index: 943246 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4934. Min Act: -0.0001

Data Index: 50465 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4922. Min Act: -0.0001

Data Index: 617930 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3832. Min Act: -0.0001

Data Index: 436750 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3789. Min Act: -0.0001

Data Index: 537243 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3636. Min Act: -0.0001

Data Index: 860427 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4724. Min Act: -0.0001

Data Index: 673126 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4308. Min Act: -0.0001

Data Index: 1015384 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3222. Min Act: -0.0001

Data Index: 1273763 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3942. Min Act: -0.0001

Data Index: 363496 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3768. Min Act: -0.0001

Data Index: 925172 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4036. Min Act: -0.0001

Data Index: 347472 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.4357. Min Act: -0.0001

Data Index: 247191 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3137. Min Act: -0.0001

Data Index: 289466 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3527. Min Act: -0.0001

Data Index: 718765 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.5879. Min Range: -1.5879

Max Act: 1.3511. Min Act: -0.0001

Data Index: 12046 (C4 (Web Text))

Max Activating Token Index: 817