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

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

Neuron 255 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.7070. Min Act: -0.0000

Data Index: 996043 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.7046. Min Act: -0.0000

Data Index: 605870 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1175340 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6442. Min Act: -0.0000

Data Index: 728645 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6041. Min Act: -0.0000

Data Index: 262391 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6123. Min Act: -0.0000

Data Index: 132303 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.6093. Min Act: -0.0000

Data Index: 876651 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1347600 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1325265 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5599. Min Act: -0.0000

Data Index: 497841 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5796. Min Act: -0.0000

Data Index: 350499 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1172067 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1132411 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5736. Min Act: -0.0000

Data Index: 307368 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5754. Min Act: -0.0000

Data Index: 432962 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1069920 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5469. Min Act: -0.0000

Data Index: 25660 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5427. Min Act: -0.0000

Data Index: 872420 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5439. Min Act: -0.0000

Data Index: 173819 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.7217. Min Range: -0.7217

Max Act: 0.5444. Min Act: -0.0000

Data Index: 330478 (C4 (Web Text))

Max Activating Token Index: 28