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

Dataset: The Pile

Neuron 2173 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: 0.5916. Min Range: -0.5916

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1633695 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4932. Min Act: -0.0000

Data Index: 511473 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1829038 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.4004. Min Act: -0.0000

Data Index: 51118 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1075360 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1701782 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1524839 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3606. Min Act: -0.0000

Data Index: 293256 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1074656 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3703. Min Act: -0.0000

Data Index: 963850 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1649591 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3398. Min Act: -0.0000

Data Index: 170033 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1446502 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3493. Min Act: -0.0000

Data Index: 500542 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3468. Min Act: -0.0000

Data Index: 7477 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3440. Min Act: -0.0000

Data Index: 205278 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1275393 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1595901 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3371. Min Act: -0.0000

Data Index: 770003 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.5916. Min Range: -0.5916

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1544679 (The Pile)

Max Activating Token Index: 382