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

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

Neuron 5753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.7164. Min Act: -0.0003

Data Index: 1204482 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6386. Min Act: -0.0002

Data Index: 895599 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6411. Min Act: -0.0002

Data Index: 1082972 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6322. Min Act: -0.0002

Data Index: 1342714 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6366. Min Act: -0.0002

Data Index: 487624 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6169. Min Act: -0.0002

Data Index: 132317 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6173. Min Act: -0.0002

Data Index: 158489 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6067. Min Act: -0.0002

Data Index: 729391 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6098. Min Act: -0.0002

Data Index: 756930 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6061. Min Act: -0.0002

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5966. Min Act: -0.0002

Data Index: 10808 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5966. Min Act: -0.0002

Data Index: 701591 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6108. Min Act: -0.0002

Data Index: 336511 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5911. Min Act: -0.0002

Data Index: 562511 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6084. Min Act: -0.0002

Data Index: 977033 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5893. Min Act: -0.0002

Data Index: 1096264 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5942. Min Act: -0.0002

Data Index: 384804 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5937. Min Act: -0.0002

Data Index: 414227 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5973. Min Act: -0.0002

Data Index: 353667 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5917. Min Act: -0.0002

Data Index: 953208 (C4 (Web Text))

Max Activating Token Index: 332