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

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

Neuron 2062 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: 4.1233. Min Range: -4.1233

Max Act: 4.1233. Min Act: -0.0000

Data Index: 161393 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 4.1233. Min Range: -4.1233

Max Act: 3.4364. Min Act: -0.0000

Data Index: 958108 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 4.1233. Min Range: -4.1233

Max Act: 3.0393. Min Act: -0.0000

Data Index: 476378 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 4.1233. Min Range: -4.1233

Max Act: 3.2239. Min Act: -0.0000

Data Index: 795399 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.8565. Min Act: -0.0001

Data Index: 1295634 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.6855. Min Act: -0.0000

Data Index: 551987 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.6256. Min Act: -0.0000

Data Index: 390092 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 4.1233. Min Range: -4.1233

Max Act: 1.9940. Min Act: -0.0000

Data Index: 66878 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.8898. Min Act: -0.0000

Data Index: 1271478 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.5844. Min Act: -0.0000

Data Index: 753808 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.9528. Min Act: -0.0000

Data Index: 476086 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.9109. Min Act: -0.0000

Data Index: 1083083 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.6164. Min Act: -0.0000

Data Index: 440712 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.6478. Min Act: -0.0000

Data Index: 1095494 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.5140. Min Act: -0.0001

Data Index: 430332 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.3302. Min Act: -0.0000

Data Index: 205626 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.3241. Min Act: -0.0000

Data Index: 333853 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.3139. Min Act: -0.0000

Data Index: 432807 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.4488. Min Act: -0.0000

Data Index: 1239106 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 4.1233. Min Range: -4.1233

Max Act: 2.5722. Min Act: -0.0000

Data Index: 313384 (C4 (Web Text))

Max Activating Token Index: 866