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

Dataset: The Pile

Neuron 1987 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: 0.4476. Min Range: -0.4476

Max Act: 0.4476. Min Act: -0.0000

Data Index: 319212 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1265329 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1930769 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1287371 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3636. Min Act: -0.0000

Data Index: 678156 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3768. Min Act: -0.0000

Data Index: 347072 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3113. Min Act: -0.0000

Data Index: 165197 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3137. Min Act: -0.0000

Data Index: 23222 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1329991 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1187554 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1813337 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2984. Min Act: -0.0000

Data Index: 806494 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3106. Min Act: -0.0000

Data Index: 730662 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3092. Min Act: -0.0000

Data Index: 260707 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1302015 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2822. Min Act: -0.0000

Data Index: 981291 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2690. Min Act: -0.0000

Data Index: 171039 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1187988 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1456145 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1307678 (The Pile)

Max Activating Token Index: 534