Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2934 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6298. Min Act: -0.0000

Data Index: 790678 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6517. Min Act: -0.0000

Data Index: 915657 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1960510 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5340. Min Act: -0.0001

Data Index: 244953 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1468032 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5272. Min Act: -0.0000

Data Index: 175521 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5095. Min Act: -0.0001

Data Index: 775413 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5158. Min Act: -0.0001

Data Index: 934159 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1866148 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4708. Min Act: -0.0000

Data Index: 10906 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1466580 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1956802 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4703. Min Act: -0.0000

Data Index: 457308 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1003152 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4513. Min Act: -0.0000

Data Index: 35370 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4652. Min Act: -0.0001

Data Index: 953187 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4577. Min Act: -0.0000

Data Index: 371158 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4893. Min Act: -0.0001

Data Index: 376604 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4729. Min Act: -0.0001

Data Index: 922115 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1526667 (The Pile)

Max Activating Token Index: 350