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

Dataset: The Pile

Neuron 1372 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: 3.2293. Min Range: -3.2293

Max Act: 3.2293. Min Act: -0.0000

Data Index: 73951 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8471. Min Act: -0.0000

Data Index: 1609667 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7473. Min Act: -0.0000

Data Index: 791630 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8623. Min Act: -0.0000

Data Index: 1721131 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8366. Min Act: -0.0000

Data Index: 408665 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.9388. Min Act: -0.0000

Data Index: 1026723 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7372. Min Act: -0.0000

Data Index: 175132 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0264. Min Act: -0.0000

Data Index: 788196 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4403. Min Act: -0.0000

Data Index: 43619 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.5018. Min Act: -0.0000

Data Index: 468570 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3734. Min Act: -0.0000

Data Index: 1105432 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6321. Min Act: -0.0000

Data Index: 1050512 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.5003. Min Act: -0.0000

Data Index: 1798367 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4695. Min Act: -0.0000

Data Index: 1281941 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4712. Min Act: -0.0000

Data Index: 1766085 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7398. Min Act: -0.0000

Data Index: 771020 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4238. Min Act: -0.0000

Data Index: 466284 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4161. Min Act: -0.0000

Data Index: 391963 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3041. Min Act: -0.0000

Data Index: 540533 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.4021. Min Act: -0.0000

Data Index: 1350280 (The Pile)

Max Activating Token Index: 608