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

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

Neuron 1271 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6860. Min Range: -4.6860

Max Act: 4.6860. Min Act: -0.0000

Data Index: 143632 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 4.6860. Min Range: -4.6860

Max Act: 4.3464. Min Act: -0.0000

Data Index: 1243575 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.4727. Min Act: -0.0000

Data Index: 449227 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.4384. Min Act: -0.0000

Data Index: 568498 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.6106. Min Act: -0.0000

Data Index: 284344 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.3547. Min Act: -0.0000

Data Index: 990964 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.6210. Min Act: -0.0000

Data Index: 1324181 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.2605. Min Act: -0.0000

Data Index: 871725 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.2885. Min Act: -0.0000

Data Index: 162731 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.1740. Min Act: -0.0000

Data Index: 990849 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.2164. Min Act: -0.0000

Data Index: 99744 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.0096. Min Act: -0.0000

Data Index: 213455 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 4.6860. Min Range: -4.6860

Max Act: 2.9455. Min Act: -0.0000

Data Index: 360418 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.0949. Min Act: -0.0000

Data Index: 1326411 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 4.6860. Min Range: -4.6860

Max Act: 2.6273. Min Act: -0.0000

Data Index: 261370 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 4.6860. Min Range: -4.6860

Max Act: 2.8511. Min Act: -0.0000

Data Index: 86621 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.0067. Min Act: -0.0000

Data Index: 381155 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 4.6860. Min Range: -4.6860

Max Act: 3.0021. Min Act: -0.0000

Data Index: 887056 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 4.6860. Min Range: -4.6860

Max Act: 2.7219. Min Act: -0.0000

Data Index: 1020431 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 4.6860. Min Range: -4.6860

Max Act: 2.7130. Min Act: -0.0000

Data Index: 385294 (C4 (Web Text))

Max Activating Token Index: 436