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

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

Neuron 1933 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: 3.7205. Min Range: -3.7205

Max Act: 3.7205. Min Act: -0.0002

Data Index: 576430 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.5491. Min Act: -0.0002

Data Index: 1160500 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.3616. Min Act: -0.0002

Data Index: 377640 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.2978. Min Act: -0.0002

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.1054. Min Act: -0.0002

Data Index: 547597 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.1176. Min Act: -0.0002

Data Index: 1232791 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.0303. Min Act: -0.0002

Data Index: 432193 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9759. Min Act: -0.0002

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9986. Min Act: -0.0002

Data Index: 822661 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.0285. Min Act: -0.0002

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.0204. Min Act: -0.0002

Data Index: 395409 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9879. Min Act: -0.0002

Data Index: 159637 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9948. Min Act: -0.0002

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8888. Min Act: -0.0002

Data Index: 43481 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9183. Min Act: -0.0002

Data Index: 118325 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.9588. Min Act: -0.0002

Data Index: 1183926 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8473. Min Act: -0.0002

Data Index: 930412 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8572. Min Act: -0.0002

Data Index: 360735 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8785. Min Act: -0.0002

Data Index: 855699 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 3.7205. Min Range: -3.7205

Max Act: 2.8140. Min Act: -0.0002

Data Index: 721808 (C4 (Web Text))

Max Activating Token Index: 659