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

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

Neuron 2993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4582. Min Act: -0.0000

Data Index: 166787 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4427. Min Act: -0.0000

Data Index: 389250 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0000

Data Index: 347455 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1093485 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3548. Min Act: -0.0000

Data Index: 480554 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1355478 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1144264 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3639. Min Act: -0.0000

Data Index: 324332 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3624. Min Act: -0.0000

Data Index: 971624 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3403. Min Act: -0.0000

Data Index: 592529 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3310. Min Act: -0.0000

Data Index: 725046 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3269. Min Act: -0.0000

Data Index: 663747 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3376. Min Act: -0.0000

Data Index: 429436 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3349. Min Act: -0.0000

Data Index: 963324 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3210. Min Act: -0.0000

Data Index: 426236 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3312. Min Act: -0.0000

Data Index: 254690 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1333773 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3272. Min Act: -0.0000

Data Index: 520685 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3493. Min Act: -0.0000

Data Index: 702088 (C4 (Web Text))

Max Activating Token Index: 210