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

Dataset: The Pile

Neuron 2427 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: 7.3345. Min Range: -7.3345

Max Act: 7.3345. Min Act: -0.0000

Data Index: 701509 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 7.3345. Min Range: -7.3345

Max Act: 6.4826. Min Act: -0.0000

Data Index: 818364 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 7.3345. Min Range: -7.3345

Max Act: 6.8775. Min Act: -0.0000

Data Index: 482934 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 7.3345. Min Range: -7.3345

Max Act: 6.8457. Min Act: -0.0000

Data Index: 1796339 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.9314. Min Act: -0.0000

Data Index: 1060772 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 7.3345. Min Range: -7.3345

Max Act: 6.1810. Min Act: -0.0000

Data Index: 1029440 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 7.3345. Min Range: -7.3345

Max Act: 6.1370. Min Act: -0.0000

Data Index: 1379576 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.8867. Min Act: -0.0000

Data Index: 1428316 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.8012. Min Act: -0.0000

Data Index: 707131 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.8490. Min Act: -0.0000

Data Index: 1395168 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.6554. Min Act: -0.0000

Data Index: 1601859 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.5845. Min Act: -0.0000

Data Index: 1660900 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 7.3345. Min Range: -7.3345

Max Act: 4.8202. Min Act: -0.0000

Data Index: 1438999 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.4940. Min Act: -0.0000

Data Index: 80592 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.5654. Min Act: -0.0000

Data Index: 455525 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.5488. Min Act: -0.0000

Data Index: 978501 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.3450. Min Act: -0.0000

Data Index: 90021 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 7.3345. Min Range: -7.3345

Max Act: 4.9949. Min Act: -0.0000

Data Index: 548599 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.3254. Min Act: -0.0000

Data Index: 1372270 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 7.3345. Min Range: -7.3345

Max Act: 5.4436. Min Act: -0.0000

Data Index: 949593 (The Pile)

Max Activating Token Index: 331