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

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

Neuron 4584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4338. Min Act: -0.0001

Data Index: 403320 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4915. Min Act: -0.0001

Data Index: 128019 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4320. Min Act: -0.0001

Data Index: 91774 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3911. Min Act: -0.0001

Data Index: 436008 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1049418 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.4103. Min Act: -0.0001

Data Index: 410122 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3969. Min Act: -0.0001

Data Index: 994906 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3490. Min Act: -0.0001

Data Index: 210085 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1032488 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3709. Min Act: -0.0001

Data Index: 834937 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3831. Min Act: -0.0001

Data Index: 514411 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3847. Min Act: -0.0001

Data Index: 819322 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3540. Min Act: -0.0001

Data Index: 836965 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3691. Min Act: -0.0001

Data Index: 831232 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3671. Min Act: -0.0001

Data Index: 447263 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3791. Min Act: -0.0001

Data Index: 719161 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3592. Min Act: -0.0001

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3418. Min Act: -0.0001

Data Index: 1265384 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3490. Min Act: -0.0001

Data Index: 187442 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.4915. Min Range: -0.4915

Max Act: 0.3678. Min Act: -0.0001

Data Index: 541658 (C4 (Web Text))

Max Activating Token Index: 195