Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2816 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.4184. Min Act: -0.0000

Data Index: 632309 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.4147. Min Act: -0.0000

Data Index: 591066 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1007237 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.2776. Min Act: -0.0000

Data Index: 700768 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.2405. Min Act: 0.0000

Data Index: 735114 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.2040. Min Act: -0.0000

Data Index: 146175 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1847. Min Act: -0.0000

Data Index: 923154 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1788. Min Act: -0.0000

Data Index: 257013 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1238. Min Act: 0.0000

Data Index: 188470 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1267. Min Act: -0.0000

Data Index: 579061 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1214. Min Act: 0.0000

Data Index: 391976 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1208. Min Act: -0.0000

Data Index: 777350 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1797. Min Act: -0.0000

Data Index: 891450 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1147168 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0942. Min Act: 0.0001

Data Index: 350259 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0889. Min Act: -0.0000

Data Index: 59728 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0873. Min Act: -0.0000

Data Index: 881191 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0548. Min Act: -0.0000

Data Index: 247589 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0944. Min Act: -0.0000

Data Index: 194282 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9570. Min Act: -0.0000

Data Index: 950084 (C4 (Web Text))

Max Activating Token Index: 316