Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3570. Min Act: -0.0001

Data Index: 173033 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1145589 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2774. Min Act: -0.0001

Data Index: 442059 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1302921 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2818. Min Act: -0.0001

Data Index: 218161 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2644. Min Act: -0.0001

Data Index: 546600 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2650. Min Act: -0.0001

Data Index: 533706 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2827. Min Act: -0.0001

Data Index: 749315 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1174428 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2652. Min Act: -0.0001

Data Index: 980417 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1094971 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2664. Min Act: -0.0001

Data Index: 810589 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2597. Min Act: -0.0001

Data Index: 925817 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2542. Min Act: -0.0001

Data Index: 15298 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2569. Min Act: -0.0001

Data Index: 331707 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2557. Min Act: -0.0001

Data Index: 971253 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1168564 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2524. Min Act: -0.0001

Data Index: 271476 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2312. Min Act: -0.0001

Data Index: 245903 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1305208 (C4 (Web Text))

Max Activating Token Index: 353