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

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

Neuron 135 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5525. Min Act: -0.0000

Data Index: 39017 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1320106 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5517. Min Act: -0.0000

Data Index: 32077 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5699. Min Act: -0.0000

Data Index: 363254 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4844. Min Act: -0.0000

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1225845 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4636. Min Act: -0.0000

Data Index: 921908 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5044. Min Act: -0.0000

Data Index: 255778 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1165164 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5234. Min Act: -0.0000

Data Index: 770589 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1100034 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4874. Min Act: -0.0000

Data Index: 479802 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4872. Min Act: -0.0000

Data Index: 755327 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1101907 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5045. Min Act: -0.0000

Data Index: 747550 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4720. Min Act: -0.0000

Data Index: 447124 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4563. Min Act: -0.0000

Data Index: 74436 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4642. Min Act: -0.0000

Data Index: 115267 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1197956 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4510. Min Act: -0.0000

Data Index: 92639 (C4 (Web Text))

Max Activating Token Index: 623