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

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

Neuron 4075 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: 1.2804. Min Range: -1.2804

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1590448 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.1690. Min Act: -0.0000

Data Index: 175941 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1080509 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0527. Min Act: -0.0000

Data Index: 308952 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0717. Min Act: -0.0000

Data Index: 934411 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0825. Min Act: -0.0000

Data Index: 342632 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1103386 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0419. Min Act: -0.0000

Data Index: 924779 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.2804. Min Range: -1.2804

Max Act: 1.0019. Min Act: -0.0000

Data Index: 1266153 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1598634 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9941. Min Act: -0.0000

Data Index: 139514 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9991. Min Act: -0.0000

Data Index: 511158 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9937. Min Act: -0.0000

Data Index: 138115 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9903. Min Act: -0.0000

Data Index: 358620 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9105. Min Act: -0.0000

Data Index: 581435 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9070. Min Act: -0.0000

Data Index: 986822 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9038. Min Act: -0.0000

Data Index: 753409 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.8731. Min Act: -0.0000

Data Index: 666126 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.8737. Min Act: -0.0000

Data Index: 833788 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.2804. Min Range: -1.2804

Max Act: 0.9237. Min Act: -0.0000

Data Index: 903121 (C4 (Web Text))

Max Activating Token Index: 919