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

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

Neuron 1253 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: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1264100 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1269786 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 997264 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1316530 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0006

Data Index: 925823 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1093135 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1075805 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1116564 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 77269 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 317755 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0005

Data Index: 450651 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 595302 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 511222 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 981385 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 450077 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0006

Data Index: 181534 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0006

Data Index: 480759 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 338700 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0067. Min Act: -0.0006

Data Index: 458567 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0006

Data Index: 680416 (C4 (Web Text))

Max Activating Token Index: 446