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

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

Neuron 3777 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: 0.7109. Min Range: -0.7109

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1208422 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1285014 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6398. Min Act: -0.0001

Data Index: 859682 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5863. Min Act: -0.0001

Data Index: 790205 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5841. Min Act: -0.0001

Data Index: 514802 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5675. Min Act: -0.0001

Data Index: 957018 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5335. Min Act: -0.0001

Data Index: 339656 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5701. Min Act: -0.0001

Data Index: 987529 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5879. Min Act: -0.0001

Data Index: 840096 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5642. Min Act: -0.0001

Data Index: 56456 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5669. Min Act: -0.0001

Data Index: 373426 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6028. Min Act: -0.0001

Data Index: 801448 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5535. Min Act: -0.0001

Data Index: 556870 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5510. Min Act: -0.0001

Data Index: 762731 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5532. Min Act: -0.0001

Data Index: 394375 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5535. Min Act: -0.0001

Data Index: 1159424 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5374. Min Act: -0.0001

Data Index: 45272 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5327. Min Act: -0.0001

Data Index: 518827 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5133. Min Act: -0.0001

Data Index: 145164 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5347. Min Act: -0.0001

Data Index: 836846 (C4 (Web Text))

Max Activating Token Index: 909