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

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

Neuron 3536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.8391. Min Act: -0.0001

Data Index: 670176 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.7476. Min Act: -0.0001

Data Index: 428341 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1029851 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5758. Min Act: -0.0001

Data Index: 486022 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5506. Min Act: -0.0001

Data Index: 363131 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.6366. Min Act: -0.0001

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5885. Min Act: -0.0001

Data Index: 151440 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5577. Min Act: -0.0001

Data Index: 1249152 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.4599. Min Act: -0.0001

Data Index: 238253 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5456. Min Act: -0.0001

Data Index: 373046 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5492. Min Act: -0.0001

Data Index: 1284141 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5355. Min Act: -0.0001

Data Index: 837137 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5159. Min Act: -0.0001

Data Index: 247240 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5125. Min Act: -0.0001

Data Index: 334533 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5434. Min Act: -0.0001

Data Index: 939599 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5234. Min Act: -0.0001

Data Index: 783437 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.5169. Min Act: -0.0001

Data Index: 877423 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.8391. Min Range: -0.8391

Max Act: 0.4822. Min Act: -0.0001

Data Index: 574657 (C4 (Web Text))

Max Activating Token Index: 155