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

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

Neuron 1360 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: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0006

Data Index: 442766 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1337217 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0006

Data Index: 66633 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 393985 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0080. Min Act: -0.0006

Data Index: 946512 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 491821 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 186017 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 323310 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 316728 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 437496 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 607520 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 642862 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 724676 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 765970 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 519433 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 402717 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 388754 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 412120 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 882850 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1270569 (C4 (Web Text))

Max Activating Token Index: 67