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

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

Neuron 3699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4890. Min Act: -0.0000

Data Index: 434202 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4185. Min Act: -0.0000

Data Index: 622630 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.4005. Min Act: -0.0000

Data Index: 617747 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3882. Min Act: -0.0000

Data Index: 313790 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3739. Min Act: -0.0000

Data Index: 864717 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3945. Min Act: -0.0000

Data Index: 459122 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3935. Min Act: -0.0000

Data Index: 345498 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3793. Min Act: -0.0000

Data Index: 621304 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3598. Min Act: -0.0000

Data Index: 294120 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1117053 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1176483 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3388. Min Act: -0.0000

Data Index: 684697 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1174527 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3503. Min Act: -0.0000

Data Index: 15422 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3490. Min Act: -0.0000

Data Index: 468239 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3469. Min Act: -0.0000

Data Index: 675615 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3245. Min Act: -0.0000

Data Index: 443738 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3317. Min Act: -0.0000

Data Index: 805880 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3312. Min Act: -0.0000

Data Index: 893406 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.4890. Min Range: -0.4890

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1073496 (C4 (Web Text))

Max Activating Token Index: 342