Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.4506. Min Act: -0.0000

Data Index: 593601 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.4322. Min Act: -0.0000

Data Index: 354289 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.5551. Min Act: -0.0000

Data Index: 802778 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.5372. Min Act: -0.0000

Data Index: 743278 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.4295. Min Act: -0.0000

Data Index: 551115 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.4932. Min Act: -0.0000

Data Index: 765073 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3660. Min Act: -0.0000

Data Index: 269382 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3977. Min Act: -0.0000

Data Index: 507966 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1031515 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3410. Min Act: -0.0000

Data Index: 801614 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.4504. Min Act: -0.0000

Data Index: 700556 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3591. Min Act: -0.0000

Data Index: 381256 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1224620 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1007731 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1129771 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1307319 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.3017. Min Act: -0.0000

Data Index: 484427 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.2508. Min Act: -0.0000

Data Index: 684810 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1201110 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 1.5551. Min Range: -1.5551

Max Act: 1.1922. Min Act: -0.0000

Data Index: 704404 (C4 (Web Text))

Max Activating Token Index: 673