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

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

Neuron 3450 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5155. Min Act: -0.0000

Data Index: 836777 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5339. Min Act: -0.0000

Data Index: 351997 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1329472 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4069. Min Act: -0.0000

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3931. Min Act: -0.0000

Data Index: 545377 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3994. Min Act: -0.0000

Data Index: 634927 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1318321 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3498. Min Act: -0.0000

Data Index: 458690 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1097618 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3546. Min Act: -0.0000

Data Index: 634753 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3695. Min Act: -0.0000

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1142205 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3449. Min Act: -0.0000

Data Index: 748319 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1121658 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3504. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3401. Min Act: -0.0000

Data Index: 240879 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1214401 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1055264 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3230. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 937