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

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

Neuron 1527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5211. Min Act: -0.0002

Data Index: 667197 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4785. Min Act: -0.0001

Data Index: 854439 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4945. Min Act: -0.0002

Data Index: 581533 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4571. Min Act: -0.0002

Data Index: 874342 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4688. Min Act: -0.0001

Data Index: 365557 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4389. Min Act: -0.0002

Data Index: 554096 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4489. Min Act: -0.0002

Data Index: 1211844 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4166. Min Act: -0.0002

Data Index: 347864 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4251. Min Act: -0.0002

Data Index: 1355095 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4378. Min Act: -0.0001

Data Index: 852329 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4223. Min Act: -0.0002

Data Index: 783186 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4468. Min Act: -0.0001

Data Index: 189469 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4108. Min Act: -0.0002

Data Index: 1166254 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3975. Min Act: -0.0002

Data Index: 126068 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3923. Min Act: -0.0002

Data Index: 1293130 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1274837 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4228. Min Act: -0.0001

Data Index: 394220 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4164. Min Act: -0.0001

Data Index: 838411 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4186. Min Act: -0.0002

Data Index: 1022454 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.4025. Min Act: -0.0002

Data Index: 865969 (C4 (Web Text))

Max Activating Token Index: 977