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

Dataset: The Pile

Neuron 2987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8898. Min Act: -0.0000

Data Index: 516080 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.9314. Min Act: -0.0000

Data Index: 906537 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7928. Min Act: -0.0000

Data Index: 225 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8315. Min Act: -0.0000

Data Index: 34008 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1947026 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1459616 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8274. Min Act: -0.0000

Data Index: 619771 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1264088 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7540. Min Act: -0.0000

Data Index: 47313 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7801. Min Act: -0.0000

Data Index: 502415 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1168423 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7158. Min Act: -0.0000

Data Index: 939394 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1226987 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1745783 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7066. Min Act: -0.0000

Data Index: 470973 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1709650 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6724. Min Act: -0.0000

Data Index: 640919 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7162. Min Act: -0.0000

Data Index: 166506 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6781. Min Act: -0.0000

Data Index: 252876 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7102. Min Act: -0.0000

Data Index: 188224 (The Pile)

Max Activating Token Index: 789