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

Dataset: The Pile

Neuron 2696 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: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0000

Data Index: 355041 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1730247 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1402233 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3549. Min Act: -0.0000

Data Index: 898065 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1164326 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1972876 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1235840 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1777499 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1331619 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1788078 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3433. Min Act: -0.0000

Data Index: 676659 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1906299 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1166409 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3431. Min Act: -0.0000

Data Index: 360809 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3312. Min Act: -0.0000

Data Index: 71816 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3319. Min Act: -0.0000

Data Index: 793414 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3285. Min Act: -0.0000

Data Index: 58044 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1354152 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3350. Min Act: -0.0000

Data Index: 40975 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.3433. Min Act: -0.0000

Data Index: 902029 (The Pile)

Max Activating Token Index: 219