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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3484. Min Range: -2.3484

Max Act: 2.3484. Min Act: -0.0000

Data Index: 32531 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 2.3484. Min Range: -2.3484

Max Act: 2.2563. Min Act: -0.0000

Data Index: 70353 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.7525. Min Act: -0.0000

Data Index: 84152 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.7570. Min Act: -0.0000

Data Index: 691563 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.7855. Min Act: -0.0000

Data Index: 596550 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.5020. Min Act: -0.0000

Data Index: 659653 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.6411. Min Act: -0.0000

Data Index: 802441 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.5476. Min Act: -0.0000

Data Index: 1230970 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1071944 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.3639. Min Act: -0.0000

Data Index: 511660 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4441. Min Act: -0.0000

Data Index: 293276 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4371. Min Act: -0.0000

Data Index: 995713 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4730. Min Act: -0.0000

Data Index: 494079 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1318760 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4617. Min Act: -0.0000

Data Index: 921056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4768. Min Act: -0.0000

Data Index: 870726 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.4030. Min Act: -0.0000

Data Index: 368568 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.3515. Min Act: -0.0000

Data Index: 862066 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1004648 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.3484. Min Range: -2.3484

Max Act: 1.3549. Min Act: -0.0000

Data Index: 93766 (C4 (Web Text))

Max Activating Token Index: 63