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

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

Neuron 4240 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: 0.7206. Min Range: -0.7206

Max Act: 0.7206. Min Act: -0.0000

Data Index: 396024 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6485. Min Act: -0.0000

Data Index: 149553 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6842. Min Act: -0.0000

Data Index: 573344 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.6036. Min Act: -0.0000

Data Index: 968879 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5838. Min Act: -0.0000

Data Index: 53254 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4993. Min Act: -0.0000

Data Index: 207412 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5270. Min Act: -0.0001

Data Index: 371082 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5274. Min Act: -0.0000

Data Index: 52770 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4857. Min Act: -0.0000

Data Index: 548999 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1199725 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4857. Min Act: -0.0001

Data Index: 645082 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5106. Min Act: -0.0000

Data Index: 341122 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5042. Min Act: -0.0000

Data Index: 747968 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5025. Min Act: -0.0000

Data Index: 232297 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1142625 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4848. Min Act: -0.0000

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4652. Min Act: -0.0000

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4654. Min Act: -0.0000

Data Index: 553878 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1028746 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.7206. Min Range: -0.7206

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1143932 (C4 (Web Text))

Max Activating Token Index: 564