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

Dataset: The Pile

Neuron 2885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1703659 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.8797. Min Act: -0.0000

Data Index: 410008 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.8335. Min Act: -0.0000

Data Index: 739103 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.8875. Min Act: -0.0000

Data Index: 536369 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7267. Min Act: -0.0000

Data Index: 953436 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.9222. Min Act: -0.0000

Data Index: 1329547 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.6346. Min Act: -0.0000

Data Index: 934671 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.6506. Min Act: -0.0000

Data Index: 1341903 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7712. Min Act: -0.0000

Data Index: 1852314 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1282977 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7291. Min Act: -0.0000

Data Index: 642027 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4452. Min Act: -0.0000

Data Index: 470598 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5214. Min Act: -0.0000

Data Index: 146955 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5312. Min Act: -0.0000

Data Index: 931593 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7956. Min Act: -0.0000

Data Index: 395452 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4879. Min Act: -0.0000

Data Index: 607180 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1484627 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3559. Min Act: -0.0000

Data Index: 319374 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3113. Min Act: -0.0000

Data Index: 921067 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5385. Min Act: -0.0000

Data Index: 183066 (The Pile)

Max Activating Token Index: 245