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

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

Neuron 1260 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.4245. Min Act: -0.0001

Data Index: 60787 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.2790. Min Act: -0.0001

Data Index: 775037 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1725. Min Act: -0.0001

Data Index: 525260 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1808. Min Act: -0.0001

Data Index: 1123645 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1897. Min Act: -0.0001

Data Index: 1058894 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0808. Min Act: -0.0001

Data Index: 846818 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0242. Min Act: -0.0001

Data Index: 416374 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0758. Min Act: -0.0001

Data Index: 158492 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0697. Min Act: -0.0001

Data Index: 153465 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.1013. Min Act: -0.0001

Data Index: 338963 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0056. Min Act: -0.0001

Data Index: 615117 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0372. Min Act: -0.0001

Data Index: 712890 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0638. Min Act: -0.0001

Data Index: 45649 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0282. Min Act: -0.0001

Data Index: 860280 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0094. Min Act: -0.0001

Data Index: 1307134 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0051. Min Act: -0.0001

Data Index: 1030440 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0254. Min Act: -0.0001

Data Index: 186070 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.4245. Min Range: -1.4245

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1359773 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0211. Min Act: -0.0001

Data Index: 1009327 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.4245. Min Range: -1.4245

Max Act: 1.0059. Min Act: -0.0001

Data Index: 311478 (C4 (Web Text))

Max Activating Token Index: 298