Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3224 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1295891 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1375687 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1099688 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1492951 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8047. Min Act: -0.0000

Data Index: 935382 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8519. Min Act: -0.0000

Data Index: 489584 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1439599 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1388734 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7351. Min Act: -0.0000

Data Index: 460624 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1575878 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1958411 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7340. Min Act: -0.0000

Data Index: 566130 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1244003 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1953034 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1697097 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1374156 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.8040. Min Act: -0.0000

Data Index: 633582 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7268. Min Act: -0.0000

Data Index: 786462 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1123249 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.9436. Min Range: -0.9436

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1171777 (The Pile)

Max Activating Token Index: 901