Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1755 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0006

Data Index: 514479 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 497280 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1222452 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 44818 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0054. Min Act: -0.0006

Data Index: 849066 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0007

Data Index: 1288302 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0006

Data Index: 321557 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0006

Data Index: 644383 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0005

Data Index: 640718 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0006

Data Index: 320769 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0047. Min Act: -0.0006

Data Index: 866867 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0006

Data Index: 100604 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0049. Min Act: -0.0006

Data Index: 524981 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0006

Data Index: 233752 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1167496 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0046. Min Act: -0.0006

Data Index: 733681 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0006

Data Index: 126958 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0048. Min Act: -0.0006

Data Index: 921620 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0047. Min Act: -0.0006

Data Index: 233801 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1144629 (C4 (Web Text))

Max Activating Token Index: 510