Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2689 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1355369 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1273977 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.8101. Min Act: -0.0001

Data Index: 525021 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7931. Min Act: -0.0001

Data Index: 22640 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1084628 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1170117 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1062409 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5963. Min Act: -0.0001

Data Index: 1276907 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6323. Min Act: -0.0000

Data Index: 648907 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6291. Min Act: -0.0000

Data Index: 207144 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6064. Min Act: -0.0000

Data Index: 412538 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1085663 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5520. Min Act: -0.0000

Data Index: 597022 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6880. Min Act: -0.0001

Data Index: 188997 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6175. Min Act: -0.0001

Data Index: 1078423 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6090. Min Act: -0.0001

Data Index: 587112 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1087438 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.5869. Min Act: -0.0001

Data Index: 534134 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6037. Min Act: -0.0001

Data Index: 442221 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6073. Min Act: -0.0000

Data Index: 941926 (C4 (Web Text))

Max Activating Token Index: 106