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

Dataset: The Pile

Neuron 2415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.3367. Min Act: -0.0000

Data Index: 577032 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1777091 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1088447 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1260227 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0352. Min Act: -0.0000

Data Index: 559053 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9735. Min Act: -0.0000

Data Index: 872759 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9819. Min Act: -0.0000

Data Index: 693660 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1263821 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9287. Min Act: -0.0000

Data Index: 110061 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9054. Min Act: -0.0000

Data Index: 183514 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8802. Min Act: -0.0000

Data Index: 281313 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9489. Min Act: -0.0000

Data Index: 264432 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9361. Min Act: -0.0000

Data Index: 143585 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9389. Min Act: -0.0000

Data Index: 289885 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1965052 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1007743 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1874771 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1701375 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9306. Min Act: -0.0000

Data Index: 66854 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8917. Min Act: -0.0000

Data Index: 753344 (The Pile)

Max Activating Token Index: 379