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

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

Neuron 1685 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: -0.0002

Data Index: 929272 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 249805 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 684989 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1046270 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 467645 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 236317 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1207483 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 83377 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 17473 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 318691 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 190263 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 956952 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 470834 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 550412 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 964111 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1219989 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 993380 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0002

Data Index: 680221 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1271345 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0003

Data Index: 348229 (C4 (Web Text))

Max Activating Token Index: 464