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

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

Neuron 4607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.7525. Min Act: -0.0000

Data Index: 378529 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.6679. Min Act: -0.0000

Data Index: 63270 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.4573. Min Act: -0.0000

Data Index: 55980 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.5977. Min Act: -0.0000

Data Index: 710805 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1256399 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.6035. Min Act: -0.0000

Data Index: 856722 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.3862. Min Act: -0.0000

Data Index: 428314 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1897. Min Act: -0.0000

Data Index: 655847 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1040381 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1329354 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.2065. Min Act: -0.0000

Data Index: 688854 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.2337. Min Act: -0.0000

Data Index: 280544 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1163280 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1154976 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1290. Min Act: -0.0000

Data Index: 202113 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1182922 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1486. Min Act: -0.0000

Data Index: 733745 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1294. Min Act: -0.0000

Data Index: 629030 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.0648. Min Act: -0.0000

Data Index: 327680 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.7525. Min Range: -1.7525

Max Act: 1.1979. Min Act: -0.0000

Data Index: 970062 (C4 (Web Text))

Max Activating Token Index: 839