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

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

Neuron 3619 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: 0.3507. Min Range: -0.3507

Max Act: 0.3507. Min Act: -0.0000

Data Index: 363152 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3123. Min Act: -0.0000

Data Index: 556070 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1238319 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3075. Min Act: -0.0000

Data Index: 934038 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1076306 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1288418 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2661. Min Act: -0.0000

Data Index: 670848 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1089141 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2498. Min Act: -0.0000

Data Index: 207560 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2755. Min Act: -0.0000

Data Index: 456262 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2592. Min Act: -0.0000

Data Index: 116733 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2584. Min Act: -0.0000

Data Index: 287428 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2663. Min Act: -0.0000

Data Index: 117749 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2534. Min Act: -0.0000

Data Index: 425873 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2437. Min Act: -0.0000

Data Index: 213882 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2426. Min Act: -0.0000

Data Index: 327566 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2444. Min Act: -0.0000

Data Index: 357774 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2268. Min Act: -0.0000

Data Index: 32119 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2423. Min Act: -0.0000

Data Index: 861905 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2317. Min Act: -0.0000

Data Index: 180323 (C4 (Web Text))

Max Activating Token Index: 600