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

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

Neuron 4704 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.2970. Min Act: -0.0000

Data Index: 366719 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.1417. Min Act: -0.0000

Data Index: 181587 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1342975 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0154. Min Act: -0.0000

Data Index: 986352 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.2970. Min Range: -1.2970

Max Act: 1.0903. Min Act: -0.0000

Data Index: 195324 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9331. Min Act: -0.0000

Data Index: 23515 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9875. Min Act: -0.0000

Data Index: 239966 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9359. Min Act: -0.0000

Data Index: 275560 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8516. Min Act: 0.0001

Data Index: 800561 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.9085. Min Act: -0.0000

Data Index: 931054 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8379. Min Act: -0.0000

Data Index: 608274 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8877. Min Act: -0.0000

Data Index: 835778 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8723. Min Act: -0.0000

Data Index: 649059 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8736. Min Act: -0.0000

Data Index: 256085 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8190. Min Act: -0.0000

Data Index: 926900 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8402. Min Act: -0.0000

Data Index: 811028 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8419. Min Act: -0.0000

Data Index: 162069 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1081974 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.7818. Min Act: -0.0000

Data Index: 487625 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.2970. Min Range: -1.2970

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1219872 (C4 (Web Text))

Max Activating Token Index: 173