Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 794 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6434. Min Act: -0.0000

Data Index: 448733 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6179. Min Act: 0.0000

Data Index: 100396 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1242414 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5529. Min Act: -0.0000

Data Index: 338110 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1348870 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5539. Min Act: -0.0000

Data Index: 434978 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1123136 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1028460 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1146115 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5419. Min Act: -0.0000

Data Index: 468247 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5203. Min Act: -0.0001

Data Index: 435667 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5529. Min Act: 0.0001

Data Index: 1349973 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5142. Min Act: 0.0001

Data Index: 839673 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5283. Min Act: -0.0000

Data Index: 813288 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5254. Min Act: -0.0000

Data Index: 160917 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1099901 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5221. Min Act: -0.0001

Data Index: 1278762 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4897. Min Act: -0.0000

Data Index: 675726 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5041. Min Act: -0.0000

Data Index: 743373 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1023721 (C4 (Web Text))

Max Activating Token Index: 938