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

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

Neuron 2130 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4906. Min Act: -0.0001

Data Index: 27028 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4555. Min Act: -0.0000

Data Index: 415007 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4503. Min Act: -0.0000

Data Index: 851811 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4307. Min Act: -0.0000

Data Index: 33472 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4204. Min Act: -0.0001

Data Index: 661390 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1295260 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3992. Min Act: -0.0001

Data Index: 833560 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4048. Min Act: -0.0000

Data Index: 973833 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4005. Min Act: -0.0000

Data Index: 582417 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3627. Min Act: -0.0001

Data Index: 589329 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3960. Min Act: -0.0000

Data Index: 777220 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1097386 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3770. Min Act: -0.0000

Data Index: 713638 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3653. Min Act: -0.0000

Data Index: 434803 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3637. Min Act: -0.0001

Data Index: 1139826 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1221936 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3508. Min Act: -0.0001

Data Index: 579160 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3521. Min Act: -0.0001

Data Index: 511258 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3498. Min Act: -0.0000

Data Index: 674962 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3546. Min Act: -0.0001

Data Index: 248201 (C4 (Web Text))

Max Activating Token Index: 53