Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4219. Min Act: -0.0000

Data Index: 184194 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3367. Min Act: -0.0000

Data Index: 798280 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1324303 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3006. Min Act: -0.0000

Data Index: 994263 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2861. Min Act: -0.0000

Data Index: 794999 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1297938 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1108196 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2686. Min Act: -0.0000

Data Index: 554979 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2836. Min Act: -0.0000

Data Index: 73501 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2571. Min Act: -0.0001

Data Index: 740749 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1276177 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2366. Min Act: -0.0000

Data Index: 353007 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2527. Min Act: -0.0000

Data Index: 610319 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2609. Min Act: -0.0000

Data Index: 882750 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2560. Min Act: -0.0000

Data Index: 178086 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2471. Min Act: -0.0000

Data Index: 892008 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1331576 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2432. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2411. Min Act: -0.0001

Data Index: 66416 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2401. Min Act: -0.0000

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 379