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

Dataset: The Pile

Neuron 1500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1360020 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8605. Min Act: -0.0000

Data Index: 749305 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1824733 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8331. Min Act: -0.0000

Data Index: 316685 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8042. Min Act: -0.0000

Data Index: 691627 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8549. Min Act: -0.0000

Data Index: 893086 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1581354 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7372. Min Act: -0.0000

Data Index: 959726 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8183. Min Act: -0.0000

Data Index: 511484 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1653596 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1096854 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1398026 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1480438 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.6911. Min Act: -0.0000

Data Index: 113401 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7306. Min Act: -0.0000

Data Index: 992823 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1157888 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7508. Min Act: -0.0000

Data Index: 19173 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7465. Min Act: -0.0000

Data Index: 183043 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.8513. Min Act: -0.0000

Data Index: 689126 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.9388. Min Range: -0.9388

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1809812 (The Pile)

Max Activating Token Index: 287