Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.7786. Min Act: -0.0000

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.7262. Min Act: -0.0000

Data Index: 82333 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6220. Min Act: -0.0000

Data Index: 282894 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6375. Min Act: -0.0000

Data Index: 242894 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5881. Min Act: -0.0000

Data Index: 449656 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6599. Min Act: -0.0000

Data Index: 895293 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5488. Min Act: -0.0000

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5670. Min Act: -0.0000

Data Index: 581443 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5597. Min Act: -0.0000

Data Index: 962912 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5479. Min Act: -0.0000

Data Index: 463593 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6092. Min Act: -0.0000

Data Index: 652025 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5642. Min Act: -0.0000

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5367. Min Act: -0.0000

Data Index: 150047 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5130. Min Act: -0.0000

Data Index: 66436 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5126. Min Act: -0.0000

Data Index: 660204 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1106766 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1011996 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.4266. Min Act: -0.0000

Data Index: 35354 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1051630 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.4845. Min Act: -0.0000

Data Index: 794001 (C4 (Web Text))

Max Activating Token Index: 250