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

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

Neuron 183 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: 1.4776. Min Range: -1.4776

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1534667 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1150447 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1105048 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0199. Min Act: -0.0000

Data Index: 324275 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1280. Min Act: -0.0000

Data Index: 797410 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0123. Min Act: -0.0000

Data Index: 517491 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0025. Min Act: -0.0000

Data Index: 619117 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1204090 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9621. Min Act: -0.0000

Data Index: 889924 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9816. Min Act: -0.0000

Data Index: 361879 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8859. Min Act: -0.0000

Data Index: 844061 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9647. Min Act: -0.0000

Data Index: 61658 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1497018 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9255. Min Act: -0.0000

Data Index: 420728 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.9085. Min Act: -0.0000

Data Index: 458650 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1250762 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8883. Min Act: -0.0000

Data Index: 484252 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8784. Min Act: -0.0000

Data Index: 27562 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8732. Min Act: -0.0000

Data Index: 90413 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.4776. Min Range: -1.4776

Max Act: 0.8167. Min Act: -0.0000

Data Index: 214679 (C4 (Web Text))

Max Activating Token Index: 281