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

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

Neuron 884 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.2519. Min Act: -0.0000

Data Index: 565631 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.2087. Min Act: -0.0000

Data Index: 149526 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.1971. Min Act: 0.0000

Data Index: 266608 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.0618. Min Act: -0.0000

Data Index: 543948 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.1160. Min Act: -0.0000

Data Index: 1325900 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.9878. Min Act: -0.0000

Data Index: 556100 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.9597. Min Act: 0.0000

Data Index: 295044 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.2519. Min Range: -2.2519

Max Act: 2.0423. Min Act: 0.0000

Data Index: 947838 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1277634 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.8972. Min Act: -0.0000

Data Index: 683526 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.8870. Min Act: -0.0000

Data Index: 308316 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.7669. Min Act: -0.0000

Data Index: 321806 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.7954. Min Act: -0.0000

Data Index: 435249 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.7934. Min Act: -0.0000

Data Index: 966138 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.8446. Min Act: -0.0000

Data Index: 773894 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1330216 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.8198. Min Act: -0.0000

Data Index: 74455 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.6932. Min Act: -0.0000

Data Index: 4914 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.6817. Min Act: -0.0000

Data Index: 736266 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.2519. Min Range: -2.2519

Max Act: 1.6417. Min Act: -0.0000

Data Index: 661581 (C4 (Web Text))

Max Activating Token Index: 77