Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1055681 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.4500. Min Act: -0.0000

Data Index: 326065 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.4522. Min Act: -0.0000

Data Index: 921247 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.4015. Min Act: -0.0000

Data Index: 387336 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3788. Min Act: -0.0000

Data Index: 427121 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3657. Min Act: -0.0001

Data Index: 348413 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1199947 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3446. Min Act: -0.0000

Data Index: 950249 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3530. Min Act: -0.0000

Data Index: 903884 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3669. Min Act: -0.0000

Data Index: 264954 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3415. Min Act: -0.0000

Data Index: 955642 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1091180 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1231803 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3376. Min Act: -0.0000

Data Index: 766813 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3463. Min Act: -0.0000

Data Index: 513367 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3479. Min Act: -0.0001

Data Index: 478795 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1289155 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3400. Min Act: -0.0000

Data Index: 879244 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3297. Min Act: -0.0000

Data Index: 918047 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.4764. Min Range: -0.4764

Max Act: 0.3303. Min Act: -0.0000

Data Index: 96869 (C4 (Web Text))

Max Activating Token Index: 943