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

Dataset: The Pile

Neuron 2930 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: 0.3708. Min Range: -0.3708

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1903385 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3448. Min Act: -0.0000

Data Index: 294693 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3708. Min Act: -0.0000

Data Index: 997977 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3306. Min Act: -0.0000

Data Index: 214409 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3258. Min Act: -0.0000

Data Index: 954059 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3053. Min Act: -0.0000

Data Index: 511811 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1459245 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1356407 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1684202 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2621. Min Act: -0.0000

Data Index: 303622 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2750. Min Act: -0.0000

Data Index: 809498 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2815. Min Act: -0.0000

Data Index: 703594 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1408794 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2778. Min Act: -0.0000

Data Index: 812380 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2570. Min Act: -0.0000

Data Index: 344573 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2157. Min Act: -0.0000

Data Index: 180017 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2640. Min Act: -0.0000

Data Index: 765130 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2537. Min Act: -0.0000

Data Index: 778740 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2610. Min Act: -0.0000

Data Index: 365792 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.3708. Min Range: -0.3708

Max Act: 0.2414. Min Act: -0.0000

Data Index: 146174 (The Pile)

Max Activating Token Index: 815