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

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

Neuron 612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.7837. Min Act: -0.0000

Data Index: 952892 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.7539. Min Act: -0.0000

Data Index: 549830 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.7232. Min Act: -0.0000

Data Index: 655947 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.6363. Min Act: -0.0000

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1309184 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.6455. Min Act: -0.0000

Data Index: 754361 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.6635. Min Act: -0.0000

Data Index: 70068 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1036835 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1207947 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5804. Min Act: -0.0000

Data Index: 715064 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1236466 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5950. Min Act: -0.0000

Data Index: 734319 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5663. Min Act: -0.0001

Data Index: 235852 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5556. Min Act: -0.0001

Data Index: 320208 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5319. Min Act: -0.0000

Data Index: 432261 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5450. Min Act: -0.0000

Data Index: 362965 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1143761 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1240734 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1214225 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.7837. Min Range: -0.7837

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1127271 (C4 (Web Text))

Max Activating Token Index: 597