Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4655. Min Act: -0.0001

Data Index: 733950 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1098074 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3767. Min Act: -0.0000

Data Index: 857460 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3682. Min Act: -0.0000

Data Index: 786126 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1009939 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3038. Min Act: -0.0000

Data Index: 645202 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3494. Min Act: -0.0000

Data Index: 211576 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3472. Min Act: -0.0000

Data Index: 612254 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3597. Min Act: -0.0000

Data Index: 309431 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3446. Min Act: -0.0000

Data Index: 949060 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3511. Min Act: -0.0001

Data Index: 409719 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3335. Min Act: -0.0001

Data Index: 268436 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3399. Min Act: -0.0001

Data Index: 872071 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3154. Min Act: -0.0000

Data Index: 727363 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3134. Min Act: -0.0001

Data Index: 680312 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1052863 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3107. Min Act: -0.0001

Data Index: 658267 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3103. Min Act: -0.0000

Data Index: 506465 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1244549 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1193084 (C4 (Web Text))

Max Activating Token Index: 769