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

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

Neuron 6 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: -0.0001

Data Index: 42065 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6472. Min Act: -0.0000

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5543. Min Act: -0.0001

Data Index: 702085 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1324818 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1219515 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5405. Min Act: -0.0000

Data Index: 578765 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5598. Min Act: -0.0001

Data Index: 305246 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5441. Min Act: -0.0000

Data Index: 984062 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5611. Min Act: -0.0001

Data Index: 378754 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5418. Min Act: -0.0001

Data Index: 321155 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5175. Min Act: -0.0001

Data Index: 1199106 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4885. Min Act: -0.0001

Data Index: 147137 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5330. Min Act: -0.0001

Data Index: 167329 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5553. Min Act: -0.0001

Data Index: 988199 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1120509 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5276. Min Act: -0.0001

Data Index: 206256 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5149. Min Act: -0.0000

Data Index: 47568 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5357. Min Act: -0.0001

Data Index: 797714 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1240852 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5301. Min Act: -0.0000

Data Index: 454814 (C4 (Web Text))

Max Activating Token Index: 485