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

Dataset: The Pile

Neuron 1933 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: 3.7285. Min Range: -3.7285

Max Act: 3.5469. Min Act: -0.0000

Data Index: 303585 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.1518. Min Act: -0.0000

Data Index: 1070316 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.4585. Min Act: -0.0000

Data Index: 1236638 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.4449. Min Act: -0.0000

Data Index: 428452 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.4578. Min Act: -0.0000

Data Index: 565877 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.1062. Min Act: -0.0000

Data Index: 1988025 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.7285. Min Act: -0.0000

Data Index: 1265062 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.3916. Min Act: -0.0000

Data Index: 1002736 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.3653. Min Act: -0.0000

Data Index: 256766 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.9596. Min Act: -0.0000

Data Index: 694118 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.9693. Min Act: -0.0000

Data Index: 175351 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.8644. Min Act: -0.0000

Data Index: 1351107 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.0848. Min Act: -0.0000

Data Index: 1211829 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.8896. Min Act: -0.0000

Data Index: 1018714 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.9678. Min Act: -0.0000

Data Index: 1459253 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 3.7285. Min Range: -3.7285

Max Act: 3.0160. Min Act: -0.0000

Data Index: 990789 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.7166. Min Act: -0.0000

Data Index: 1260501 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.8613. Min Act: -0.0000

Data Index: 1773656 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.7721. Min Act: -0.0000

Data Index: 1126469 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 3.7285. Min Range: -3.7285

Max Act: 2.6207. Min Act: -0.0000

Data Index: 458542 (The Pile)

Max Activating Token Index: 140