Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.8381. Min Act: -0.0000

Data Index: 299715 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1095538 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7937. Min Act: -0.0000

Data Index: 323948 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7236. Min Act: 0.0000

Data Index: 1347292 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1026219 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6710. Min Act: -0.0000

Data Index: 218923 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6944. Min Act: -0.0000

Data Index: 891229 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1063389 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7111. Min Act: -0.0000

Data Index: 794408 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6666. Min Act: -0.0000

Data Index: 697199 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1341768 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7035. Min Act: -0.0000

Data Index: 347779 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6448. Min Act: -0.0000

Data Index: 880479 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6612. Min Act: -0.0000

Data Index: 330233 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1110508 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6431. Min Act: -0.0000

Data Index: 850364 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6522. Min Act: -0.0000

Data Index: 170111 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1876433 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6261. Min Act: -0.0000

Data Index: 251764 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1353141 (The Pile)

Max Activating Token Index: 87