Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 371 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0006

Data Index: 546238 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0460. Min Act: -0.0006

Data Index: 38594 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0440. Min Act: -0.0006

Data Index: 254352 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0449. Min Act: -0.0006

Data Index: 182031 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0457. Min Act: -0.0006

Data Index: 683350 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0445. Min Act: -0.0006

Data Index: 365802 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0006

Data Index: 736970 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0423. Min Act: -0.0006

Data Index: 999097 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0444. Min Act: -0.0006

Data Index: 416061 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0444. Min Act: -0.0006

Data Index: 125916 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0425. Min Act: -0.0006

Data Index: 1164829 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0433. Min Act: -0.0006

Data Index: 182257 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1129262 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0427. Min Act: -0.0006

Data Index: 626897 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0420. Min Act: -0.0006

Data Index: 619251 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0425. Min Act: -0.0006

Data Index: 357010 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0439. Min Act: -0.0006

Data Index: 1207638 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0439. Min Act: -0.0006

Data Index: 798733 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0438. Min Act: -0.0006

Data Index: 440036 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0428. Min Act: -0.0006

Data Index: 732533 (C4 (Web Text))

Max Activating Token Index: 245