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

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

Neuron 1171 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.2610. Min Act: -0.0000

Data Index: 423811 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0391. Min Act: -0.0000

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 1.2610. Min Range: -1.2610

Max Act: 1.0434. Min Act: -0.0000

Data Index: 190842 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8579. Min Act: -0.0000

Data Index: 274030 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9993. Min Act: -0.0000

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8913. Min Act: -0.0000

Data Index: 119615 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9570. Min Act: -0.0000

Data Index: 946945 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8277. Min Act: -0.0000

Data Index: 870373 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8933. Min Act: -0.0000

Data Index: 153105 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1236405 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.9320. Min Act: -0.0000

Data Index: 695535 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8193. Min Act: -0.0000

Data Index: 780811 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1095498 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1091384 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1144567 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8790. Min Act: -0.0000

Data Index: 127014 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8220. Min Act: -0.0000

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.2610. Min Range: -1.2610

Max Act: 0.8753. Min Act: -0.0000

Data Index: 263819 (C4 (Web Text))

Max Activating Token Index: 296