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

Dataset: The Pile

Neuron 4720 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: 5.2345. Min Range: -5.2345

Max Act: 5.0523. Min Act: -0.0000

Data Index: 110897 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 5.2345. Min Range: -5.2345

Max Act: 5.2345. Min Act: -0.0000

Data Index: 1204216 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 5.2345. Min Range: -5.2345

Max Act: 5.0662. Min Act: -0.0000

Data Index: 354049 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.7170. Min Act: -0.0000

Data Index: 548339 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 5.2345. Min Range: -5.2345

Max Act: 5.2226. Min Act: -0.0000

Data Index: 660879 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.7410. Min Act: -0.0000

Data Index: 500890 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.5592. Min Act: -0.0000

Data Index: 1423450 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.4217. Min Act: -0.0000

Data Index: 1173508 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.1684. Min Act: -0.0000

Data Index: 1833148 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.1538. Min Act: -0.0000

Data Index: 1137568 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.2528. Min Act: -0.0000

Data Index: 1922773 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.9890. Min Act: -0.0000

Data Index: 1546326 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.9035. Min Act: -0.0000

Data Index: 232786 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.7337. Min Act: -0.0000

Data Index: 377443 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.8343. Min Act: -0.0000

Data Index: 1956158 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.7669. Min Act: -0.0000

Data Index: 1988232 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.0115. Min Act: -0.0000

Data Index: 512171 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.5758. Min Act: -0.0000

Data Index: 1268368 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 5.2345. Min Range: -5.2345

Max Act: 4.0253. Min Act: -0.0000

Data Index: 1999263 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 5.2345. Min Range: -5.2345

Max Act: 3.7444. Min Act: -0.0000

Data Index: 911853 (The Pile)

Max Activating Token Index: 479