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

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

Neuron 3689 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: 5.9134. Min Range: -5.9134

Max Act: 5.9134. Min Act: -0.0000

Data Index: 1351101 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 5.9134. Min Range: -5.9134

Max Act: 5.0452. Min Act: -0.0001

Data Index: 1058859 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 5.9134. Min Range: -5.9134

Max Act: 5.1781. Min Act: -0.0000

Data Index: 1269596 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 5.9134. Min Range: -5.9134

Max Act: 5.7058. Min Act: -0.0001

Data Index: 948425 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.3118. Min Act: -0.0001

Data Index: 547874 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.2300. Min Act: -0.0001

Data Index: 221979 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.5637. Min Act: -0.0001

Data Index: 630036 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.8951. Min Act: -0.0000

Data Index: 1216239 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.6984. Min Act: -0.0001

Data Index: 749404 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.8600. Min Act: -0.0000

Data Index: 147431 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.2266. Min Act: -0.0001

Data Index: 1141375 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.6367. Min Act: -0.0000

Data Index: 817135 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.4529. Min Act: -0.0000

Data Index: 174776 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.4625. Min Act: -0.0000

Data Index: 591573 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.0855. Min Act: -0.0000

Data Index: 662314 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.5562. Min Act: -0.0001

Data Index: 168078 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.2376. Min Act: -0.0000

Data Index: 1119372 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 5.9134. Min Range: -5.9134

Max Act: 3.8564. Min Act: -0.0001

Data Index: 584804 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.2377. Min Act: -0.0000

Data Index: 295930 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.9134. Min Range: -5.9134

Max Act: 4.2364. Min Act: -0.0001

Data Index: 988524 (C4 (Web Text))

Max Activating Token Index: 332