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

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

Neuron 327 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3935. Min Range: -4.3935

Max Act: 4.3935. Min Act: -0.0000

Data Index: 1148894 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.5452. Min Act: -0.0000

Data Index: 888648 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.6579. Min Act: -0.0000

Data Index: 812904 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.6033. Min Act: -0.0000

Data Index: 881483 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.5241. Min Act: -0.0000

Data Index: 172394 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.3538. Min Act: -0.0000

Data Index: 832568 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.3611. Min Act: -0.0000

Data Index: 671627 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.8817. Min Act: -0.0000

Data Index: 304993 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.7984. Min Act: -0.0000

Data Index: 604909 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.6552. Min Act: -0.0000

Data Index: 1253721 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.7424. Min Act: -0.0000

Data Index: 1063901 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 4.3935. Min Range: -4.3935

Max Act: 3.0543. Min Act: -0.0000

Data Index: 230483 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.6793. Min Act: -0.0000

Data Index: 302881 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.8009. Min Act: -0.0000

Data Index: 200485 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.6841. Min Act: -0.0000

Data Index: 359911 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.5153. Min Act: -0.0000

Data Index: 988719 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.6529. Min Act: -0.0000

Data Index: 177649 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.7641. Min Act: -0.0000

Data Index: 621121 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.7306. Min Act: -0.0000

Data Index: 951863 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 4.3935. Min Range: -4.3935

Max Act: 2.7019. Min Act: -0.0000

Data Index: 489928 (C4 (Web Text))

Max Activating Token Index: 917