Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0006

Data Index: 299817 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0006

Data Index: 75320 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0006

Data Index: 268052 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1051466 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1104224 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 454710 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 62465 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1104549 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1340789 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1409814 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 520815 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1013817 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 372461 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 318883 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0006

Data Index: 606200 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1652627 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 915727 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 761095 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1218035 (C4 (Web Text))

Max Activating Token Index: 78