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

Dataset: The Pile

Neuron 3823 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: 1.0304. Min Range: -1.0304

Max Act: 1.0304. Min Act: -0.0000

Data Index: 970252 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1794591 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9887. Min Act: -0.0000

Data Index: 269583 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9402. Min Act: -0.0000

Data Index: 648233 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 1.0304. Min Range: -1.0304

Max Act: 1.0217. Min Act: -0.0000

Data Index: 181333 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9664. Min Act: -0.0000

Data Index: 679845 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1327741 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1974512 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1423584 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1374443 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1109432 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8779. Min Act: -0.0000

Data Index: 172075 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1102617 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1500258 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1856184 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1044666 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8608. Min Act: -0.0000

Data Index: 512642 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1406745 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8514. Min Act: -0.0000

Data Index: 683755 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8197. Min Act: -0.0000

Data Index: 667203 (The Pile)

Max Activating Token Index: 263