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

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

Neuron 5676 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1272248 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0000

Data Index: 421422 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1416. Min Act: -0.0000

Data Index: 910582 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1390. Min Act: -0.0000

Data Index: 216195 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1440. Min Act: -0.0000

Data Index: 431609 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1092933 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1216. Min Act: -0.0000

Data Index: 786249 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1229603 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1152. Min Act: -0.0000

Data Index: 3880 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1159. Min Act: -0.0000

Data Index: 608278 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1093923 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1158. Min Act: -0.0000

Data Index: 75167 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1155. Min Act: -0.0000

Data Index: 186606 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1064. Min Act: -0.0000

Data Index: 680017 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1023. Min Act: -0.0000

Data Index: 751314 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1078. Min Act: -0.0000

Data Index: 684234 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1040. Min Act: -0.0000

Data Index: 793048 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1101. Min Act: -0.0000

Data Index: 779162 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1011. Min Act: -0.0000

Data Index: 725917 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1051. Min Act: -0.0000

Data Index: 311664 (C4 (Web Text))

Max Activating Token Index: 759