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

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

Neuron 270 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1912. Min Range: -1.1912

Max Act: 1.1912. Min Act: -0.0000

Data Index: 951278 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 1.1912. Min Range: -1.1912

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1279139 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8529. Min Act: -0.0000

Data Index: 530673 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.9029. Min Act: -0.0000

Data Index: 379404 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8969. Min Act: -0.0000

Data Index: 507320 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1147648 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8307. Min Act: -0.0000

Data Index: 244317 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1138999 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1126721 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1310124 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1290740 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1116157 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8043. Min Act: -0.0000

Data Index: 213375 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7544. Min Act: -0.0000

Data Index: 16617 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7967. Min Act: -0.0000

Data Index: 295464 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1323601 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7346. Min Act: -0.0000

Data Index: 327208 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1202014 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7181. Min Act: -0.0000

Data Index: 110369 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7206. Min Act: -0.0000

Data Index: 425258 (C4 (Web Text))

Max Activating Token Index: 679