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

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

Neuron 4703 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1280800 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1068033 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3427. Min Act: -0.0000

Data Index: 80191 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1170291 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1077495 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3348. Min Act: -0.0000

Data Index: 192396 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1544710 (Python Code)

Max Activating Token Index: 552

Text #7

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3333. Min Act: -0.0000

Data Index: 180512 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3406. Min Act: -0.0000

Data Index: 286008 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3085. Min Act: -0.0000

Data Index: 306151 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3010. Min Act: -0.0000

Data Index: 757872 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1342122 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3276. Min Act: -0.0000

Data Index: 778173 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3142. Min Act: -0.0000

Data Index: 223463 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2882. Min Act: -0.0000

Data Index: 297683 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3130. Min Act: -0.0000

Data Index: 612690 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1651335 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3113. Min Act: -0.0000

Data Index: 591550 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2991. Min Act: -0.0000

Data Index: 140208 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3088. Min Act: -0.0000

Data Index: 385309 (C4 (Web Text))

Max Activating Token Index: 514