Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 309 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0000

Data Index: 867742 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0948. Min Act: -0.0000

Data Index: 532616 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0951. Min Act: -0.0000

Data Index: 161438 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0906. Min Act: -0.0000

Data Index: 877317 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0910. Min Act: -0.0000

Data Index: 608340 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1243307 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0830. Min Act: -0.0001

Data Index: 179438 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0886. Min Act: -0.0000

Data Index: 984256 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0920. Min Act: -0.0000

Data Index: 759480 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1007426 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0871. Min Act: -0.0000

Data Index: 330705 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0867. Min Act: -0.0000

Data Index: 536176 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0853. Min Act: -0.0000

Data Index: 365980 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0822. Min Act: -0.0000

Data Index: 460318 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0841. Min Act: -0.0000

Data Index: 239740 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0822. Min Act: -0.0000

Data Index: 971620 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0811. Min Act: -0.0001

Data Index: 278158 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0817. Min Act: -0.0000

Data Index: 816225 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1175670 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0838. Min Act: -0.0000

Data Index: 364234 (C4 (Web Text))

Max Activating Token Index: 669