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

Dataset: The Pile

Neuron 1263 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3425. Min Act: -0.0000

Data Index: 311167 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1272639 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1626551 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2974. Min Act: -0.0000

Data Index: 867416 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1291694 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1630468 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3219. Min Act: -0.0000

Data Index: 179361 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2996. Min Act: -0.0000

Data Index: 85602 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3375. Min Act: -0.0000

Data Index: 296205 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3272. Min Act: -0.0000

Data Index: 201243 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2977. Min Act: -0.0000

Data Index: 319426 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3244. Min Act: -0.0000

Data Index: 532621 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1592645 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3120. Min Act: -0.0000

Data Index: 36869 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1406003 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1881665 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2986. Min Act: -0.0000

Data Index: 482919 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1657584 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1908368 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1518494 (The Pile)

Max Activating Token Index: 700