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

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

Neuron 3139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1438. Min Range: -1.1438

Max Act: 1.1438. Min Act: -0.0000

Data Index: 699275 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8606. Min Act: -0.0000

Data Index: 339075 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.9043. Min Act: -0.0000

Data Index: 432389 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1330375 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1102918 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1191081 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8266. Min Act: -0.0000

Data Index: 816429 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8287. Min Act: -0.0000

Data Index: 942935 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7545. Min Act: -0.0000

Data Index: 853438 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7541. Min Act: -0.0000

Data Index: 197143 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7705. Min Act: -0.0000

Data Index: 607900 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7870. Min Act: -0.0000

Data Index: 393190 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7865. Min Act: -0.0000

Data Index: 218231 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8062. Min Act: -0.0000

Data Index: 905220 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7818. Min Act: -0.0000

Data Index: 69171 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7662. Min Act: -0.0000

Data Index: 47216 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1009810 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7507. Min Act: -0.0000

Data Index: 444164 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8135. Min Act: -0.0000

Data Index: 111145 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7381. Min Act: -0.0000

Data Index: 183426 (C4 (Web Text))

Max Activating Token Index: 752