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

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

Neuron 3750 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1308891 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1181897 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1319701 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5572. Min Act: -0.0000

Data Index: 783751 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1327609 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1118544 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5133. Min Act: -0.0000

Data Index: 61579 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5439. Min Act: -0.0000

Data Index: 567861 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5554. Min Act: -0.0000

Data Index: 511672 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5216. Min Act: -0.0000

Data Index: 249864 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5299. Min Act: -0.0000

Data Index: 256877 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1246970 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5296. Min Act: -0.0000

Data Index: 317641 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5537. Min Act: -0.0000

Data Index: 581729 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5392. Min Act: -0.0000

Data Index: 373964 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5372. Min Act: -0.0000

Data Index: 732721 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5347. Min Act: -0.0000

Data Index: 158444 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5106. Min Act: -0.0000

Data Index: 209083 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5500. Min Act: -0.0000

Data Index: 105039 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5288. Min Act: -0.0000

Data Index: 195439 (C4 (Web Text))

Max Activating Token Index: 30