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

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

Neuron 3106 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1173690 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5772. Min Act: -0.0000

Data Index: 54194 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1183159 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1152386 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5199. Min Act: -0.0000

Data Index: 646292 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5359. Min Act: -0.0000

Data Index: 596971 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5663. Min Act: -0.0000

Data Index: 844501 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5267. Min Act: -0.0000

Data Index: 771943 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1200856 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5287. Min Act: -0.0000

Data Index: 402764 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1291473 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4940. Min Act: -0.0000

Data Index: 443050 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4983. Min Act: -0.0000

Data Index: 252417 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4905. Min Act: -0.0000

Data Index: 786008 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4888. Min Act: -0.0000

Data Index: 442933 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1209707 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4467. Min Act: -0.0000

Data Index: 572112 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4459. Min Act: -0.0000

Data Index: 2658 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1264212 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1278115 (C4 (Web Text))

Max Activating Token Index: 935