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

Dataset: The Pile

Neuron 3442 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1595. Min Range: -1.1595

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1581398 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.1595. Min Range: -1.1595

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1673103 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.1595. Min Range: -1.1595

Max Act: 1.0080. Min Act: -0.0000

Data Index: 609804 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.1595. Min Range: -1.1595

Max Act: 1.0307. Min Act: -0.0000

Data Index: 255905 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.1595. Min Range: -1.1595

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1706697 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.9630. Min Act: 0.0000

Data Index: 974254 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.9494. Min Act: -0.0000

Data Index: 562408 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.9076. Min Act: -0.0000

Data Index: 140039 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.8995. Min Act: -0.0000

Data Index: 438594 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.8562. Min Act: -0.0000

Data Index: 576512 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.9575. Min Act: 0.0000

Data Index: 583445 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.8213. Min Act: -0.0000

Data Index: 528591 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7728. Min Act: -0.0000

Data Index: 396501 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.8031. Min Act: -0.0000

Data Index: 561918 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7506. Min Act: -0.0000

Data Index: 701624 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1302234 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7932. Min Act: -0.0000

Data Index: 237255 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1825214 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7374. Min Act: -0.0000

Data Index: 208108 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.1595. Min Range: -1.1595

Max Act: 0.7541. Min Act: -0.0000

Data Index: 70739 (The Pile)

Max Activating Token Index: 917