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

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

Neuron 1517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.8734. Min Act: -0.0000

Data Index: 1262033 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.8419. Min Act: -0.0000

Data Index: 1379208 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.7717. Min Act: -0.0000

Data Index: 740870 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.7250. Min Act: -0.0000

Data Index: 1386433 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.6009. Min Act: -0.0000

Data Index: 1583548 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3972. Min Act: -0.0000

Data Index: 1079621 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.3920. Min Act: -0.0000

Data Index: 305137 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2302. Min Act: -0.0000

Data Index: 1285667 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1960. Min Act: -0.0000

Data Index: 769924 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1109803 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1922. Min Act: -0.0000

Data Index: 822949 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2937. Min Act: -0.0000

Data Index: 88109 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.0548. Min Act: -0.0000

Data Index: 223060 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2962. Min Act: -0.0000

Data Index: 771641 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2727. Min Act: -0.0000

Data Index: 683979 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1484. Min Act: -0.0000

Data Index: 645762 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.1672. Min Act: -0.0000

Data Index: 1269741 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2578. Min Act: -0.0000

Data Index: 592816 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1024749 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.8734. Min Range: -2.8734

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1095013 (C4 (Web Text))

Max Activating Token Index: 8