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

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

Neuron 3096 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.5349. Min Act: -0.0001

Data Index: 918110 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.5624. Min Act: -0.0001

Data Index: 1530106 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.5309. Min Act: -0.0001

Data Index: 16939 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4660. Min Act: -0.0001

Data Index: 471022 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4418. Min Act: -0.0001

Data Index: 1144487 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4083. Min Act: -0.0001

Data Index: 833678 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3215. Min Act: -0.0001

Data Index: 1038794 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.4479. Min Act: -0.0001

Data Index: 384446 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3163. Min Act: -0.0001

Data Index: 272723 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3848. Min Act: -0.0001

Data Index: 628580 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3310. Min Act: -0.0001

Data Index: 1244966 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2457. Min Act: -0.0001

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2845. Min Act: -0.0001

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.3459. Min Act: -0.0001

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2527. Min Act: -0.0001

Data Index: 467149 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2468. Min Act: -0.0001

Data Index: 1062412 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2228. Min Act: -0.0001

Data Index: 343651 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.2625. Min Act: -0.0001

Data Index: 703368 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1275942 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.5624. Min Range: -1.5624

Max Act: 1.1762. Min Act: -0.0001

Data Index: 717988 (C4 (Web Text))

Max Activating Token Index: 353