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

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

Neuron 3915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0220. Min Range: -1.0220

Max Act: 1.0194. Min Act: -0.0001

Data Index: 1168757 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.0220. Min Range: -1.0220

Max Act: 1.0220. Min Act: -0.0001

Data Index: 1342627 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9681. Min Act: -0.0001

Data Index: 815315 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8910. Min Act: -0.0001

Data Index: 194545 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1283347 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9987. Min Act: -0.0001

Data Index: 1004140 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1313249 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9531. Min Act: -0.0001

Data Index: 309734 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9291. Min Act: -0.0001

Data Index: 984150 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9390. Min Act: -0.0001

Data Index: 1151407 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1137780 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9223. Min Act: -0.0001

Data Index: 757666 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8905. Min Act: -0.0001

Data Index: 124148 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9067. Min Act: -0.0001

Data Index: 92493 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8276. Min Act: -0.0001

Data Index: 175789 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8552. Min Act: -0.0001

Data Index: 776637 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8447. Min Act: -0.0001

Data Index: 428653 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8490. Min Act: -0.0001

Data Index: 508734 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1151627 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1273269 (C4 (Web Text))

Max Activating Token Index: 366