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

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

Neuron 4911 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.6308. Min Act: -0.0000

Data Index: 151341 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.5131. Min Act: -0.0000

Data Index: 269952 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1074345 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1263162 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3645. Min Act: -0.0000

Data Index: 113618 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3682. Min Act: -0.0000

Data Index: 831099 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1333740 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3345. Min Act: -0.0000

Data Index: 558145 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3354. Min Act: -0.0000

Data Index: 132652 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3543. Min Act: 0.0000

Data Index: 734499 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3576. Min Act: -0.0000

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1299979 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1349558 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3421. Min Act: -0.0000

Data Index: 659591 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3398. Min Act: -0.0000

Data Index: 406921 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3365. Min Act: -0.0000

Data Index: 300977 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3409. Min Act: -0.0000

Data Index: 595508 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3156. Min Act: -0.0000

Data Index: 781298 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1215078 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.6308. Min Range: -0.6308

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1132750 (C4 (Web Text))

Max Activating Token Index: 1019