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

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

Neuron 485 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1152304 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0006

Data Index: 409577 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 288545 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0006

Data Index: 283434 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 315197 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0006

Data Index: 697950 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0006

Data Index: 761504 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1203957 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0006

Data Index: 824150 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0006

Data Index: 332468 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 306298 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0006

Data Index: 444901 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 430667 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 526016 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 906552 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0006

Data Index: 75354 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1056625 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 742113 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0055. Min Act: -0.0006

Data Index: 388991 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1312941 (C4 (Web Text))

Max Activating Token Index: 485