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

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

Neuron 6028 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.8066. Min Act: -0.0000

Data Index: 401920 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5752. Min Act: -0.0000

Data Index: 683708 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1034236 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1169822 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5180. Min Act: -0.0000

Data Index: 658762 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4828. Min Act: -0.0000

Data Index: 509013 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1203717 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4316. Min Act: -0.0000

Data Index: 304324 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4507. Min Act: -0.0000

Data Index: 279693 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1273282 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3936. Min Act: -0.0000

Data Index: 856387 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3958. Min Act: -0.0000

Data Index: 174586 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3869. Min Act: -0.0000

Data Index: 293446 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1257314 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3888. Min Act: -0.0000

Data Index: 415445 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4136. Min Act: -0.0000

Data Index: 161692 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3874. Min Act: -0.0000

Data Index: 537464 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3364. Min Act: -0.0000

Data Index: 771605 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3694. Min Act: -0.0000

Data Index: 72772 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1072441 (C4 (Web Text))

Max Activating Token Index: 1003