Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2327 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.8468. Min Act: -0.0000

Data Index: 178933 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6439. Min Act: -0.0000

Data Index: 421174 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6759. Min Act: -0.0000

Data Index: 180890 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6773. Min Act: -0.0000

Data Index: 661982 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1076215 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1279690 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5557. Min Act: -0.0000

Data Index: 454027 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5468. Min Act: -0.0000

Data Index: 705014 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5907. Min Act: -0.0000

Data Index: 654643 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5868. Min Act: -0.0000

Data Index: 38591 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6045. Min Act: -0.0000

Data Index: 656498 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1344262 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1062078 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5487. Min Act: -0.0000

Data Index: 294779 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1052656 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1268125 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5667. Min Act: -0.0000

Data Index: 819105 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1319640 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.4901. Min Act: -0.0000

Data Index: 253704 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.8468. Min Range: -0.8468

Max Act: 0.5043. Min Act: -0.0000

Data Index: 640214 (C4 (Web Text))

Max Activating Token Index: 994