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

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

Neuron 1295 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1182. Min Range: -1.1182

Max Act: 1.1182. Min Act: -0.0000

Data Index: 479213 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.1182. Min Range: -1.1182

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1128992 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.1182. Min Range: -1.1182

Max Act: 1.0368. Min Act: -0.0000

Data Index: 371345 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.9981. Min Act: -0.0000

Data Index: 987500 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.9649. Min Act: -0.0000

Data Index: 322780 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.9867. Min Act: -0.0000

Data Index: 613119 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8904. Min Act: -0.0000

Data Index: 975566 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.9357. Min Act: -0.0000

Data Index: 600547 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8987. Min Act: -0.0000

Data Index: 73310 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8916. Min Act: -0.0000

Data Index: 74657 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1101062 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1131920 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1250433 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8871. Min Act: -0.0000

Data Index: 332876 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1072469 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8685. Min Act: -0.0000

Data Index: 710134 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1156900 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8622. Min Act: -0.0000

Data Index: 870911 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8308. Min Act: -0.0000

Data Index: 284378 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.1182. Min Range: -1.1182

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1086895 (C4 (Web Text))

Max Activating Token Index: 632