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

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

Neuron 4340 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1010955 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0904. Min Act: -0.0001

Data Index: 706364 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1068291 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0862. Min Act: -0.0001

Data Index: 619016 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1111361 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0843. Min Act: -0.0001

Data Index: 26242 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1079234 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0874. Min Act: -0.0001

Data Index: 244054 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1146283 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0764. Min Act: -0.0001

Data Index: 656020 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0795. Min Act: -0.0001

Data Index: 866831 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0818. Min Act: -0.0001

Data Index: 169577 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1207233 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1329835 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0724. Min Act: -0.0001

Data Index: 728006 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1047521 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1281502 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0799. Min Act: -0.0001

Data Index: 847539 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0766. Min Act: -0.0001

Data Index: 710936 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0743. Min Act: -0.0001

Data Index: 152259 (C4 (Web Text))

Max Activating Token Index: 263