Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3523 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 940314 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1094363 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 514960 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0002

Data Index: 21115 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 266720 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0002

Data Index: 47496 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0002

Data Index: 426926 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 625181 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 346263 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1157409 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0002

Data Index: 116006 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0002

Data Index: 682898 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0003

Data Index: 913279 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 191323 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 913588 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0003

Data Index: 242305 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1270598 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0002

Data Index: 240656 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 921403 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1210697 (C4 (Web Text))

Max Activating Token Index: 495