Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 105 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0488. Min Range: -1.0488

Max Act: 1.0129. Min Act: -0.0000

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.0488. Min Range: -1.0488

Max Act: 1.0488. Min Act: -0.0000

Data Index: 838588 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.0488. Min Range: -1.0488

Max Act: 1.0015. Min Act: -0.0000

Data Index: 54404 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.0488. Min Range: -1.0488

Max Act: 1.0186. Min Act: -0.0000

Data Index: 482028 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.9313. Min Act: -0.0000

Data Index: 860860 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1010224 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.9231. Min Act: -0.0000

Data Index: 142902 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.9915. Min Act: -0.0000

Data Index: 631152 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8972. Min Act: -0.0000

Data Index: 605975 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.9681. Min Act: -0.0000

Data Index: 801837 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.9275. Min Act: -0.0000

Data Index: 457043 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8769. Min Act: -0.0000

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.7893. Min Act: -0.0000

Data Index: 684091 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8600. Min Act: -0.0000

Data Index: 47782 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1207848 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.5297. Min Act: -0.0000

Data Index: 152014 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.4069. Min Act: -0.0000

Data Index: 728260 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.4246. Min Act: -0.0000

Data Index: 920413 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1005488 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1104197 (C4 (Web Text))

Max Activating Token Index: 972