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

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

Neuron 1504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.2458. Min Act: -0.0001

Data Index: 902535 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1676. Min Act: -0.0001

Data Index: 222168 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.0950. Min Act: -0.0001

Data Index: 579420 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1070. Min Act: -0.0001

Data Index: 144661 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1081. Min Act: -0.0001

Data Index: 271179 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9857. Min Act: -0.0001

Data Index: 1066456 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9030. Min Act: -0.0001

Data Index: 850726 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.0117. Min Act: -0.0001

Data Index: 5455 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9367. Min Act: -0.0001

Data Index: 1309052 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9673. Min Act: -0.0001

Data Index: 890711 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9237. Min Act: -0.0001

Data Index: 619840 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.2458. Min Range: -1.2458

Max Act: 1.1070. Min Act: -0.0001

Data Index: 708392 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9765. Min Act: -0.0001

Data Index: 865413 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8968. Min Act: -0.0001

Data Index: 151317 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9078. Min Act: -0.0001

Data Index: 226040 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1000017 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.9729. Min Act: -0.0001

Data Index: 433567 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8816. Min Act: -0.0001

Data Index: 350171 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8522. Min Act: -0.0001

Data Index: 542131 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.2458. Min Range: -1.2458

Max Act: 0.8771. Min Act: -0.0001

Data Index: 244742 (C4 (Web Text))

Max Activating Token Index: 572