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

Dataset: The Pile

Neuron 2266 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: 0.2035. Min Range: -0.2035

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1715404 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1470. Min Act: -0.0000

Data Index: 256590 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1803445 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1964896 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1340. Min Act: -0.0000

Data Index: 980317 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1445. Min Act: -0.0000

Data Index: 616822 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1684235 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1055768 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1624498 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1998036 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1377. Min Act: -0.0000

Data Index: 288313 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1425. Min Act: -0.0000

Data Index: 937172 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1451. Min Act: -0.0000

Data Index: 695928 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1356. Min Act: -0.0000

Data Index: 349392 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1457. Min Act: -0.0000

Data Index: 164879 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1887105 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1269. Min Act: -0.0000

Data Index: 721810 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1882069 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1807140 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1238. Min Act: -0.0000

Data Index: 668479 (The Pile)

Max Activating Token Index: 876