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

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

Neuron 5043 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: 2.9935. Min Range: -2.9935

Max Act: 2.9935. Min Act: -0.0000

Data Index: 487157 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.9227. Min Act: -0.0000

Data Index: 425198 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.3586. Min Act: -0.0000

Data Index: 165538 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.1913. Min Act: -0.0000

Data Index: 615372 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.0331. Min Act: -0.0000

Data Index: 760708 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.0967. Min Act: -0.0000

Data Index: 122897 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.9133. Min Act: -0.0000

Data Index: 927740 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.9920. Min Act: -0.0000

Data Index: 1345789 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.9935. Min Range: -2.9935

Max Act: 2.0780. Min Act: -0.0000

Data Index: 1020841 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.8635. Min Act: -0.0000

Data Index: 659175 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.8641. Min Act: -0.0000

Data Index: 676237 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.9750. Min Act: -0.0000

Data Index: 346407 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.8282. Min Act: -0.0000

Data Index: 797639 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.8363. Min Act: -0.0000

Data Index: 682272 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.7911. Min Act: 0.0000

Data Index: 772762 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.7705. Min Act: -0.0000

Data Index: 132335 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.6149. Min Act: -0.0000

Data Index: 869525 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1105108 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.5864. Min Act: -0.0000

Data Index: 104308 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.9935. Min Range: -2.9935

Max Act: 1.7701. Min Act: -0.0000

Data Index: 165192 (C4 (Web Text))

Max Activating Token Index: 929