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

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

Neuron 1894 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.2881. Min Act: -0.0001

Data Index: 889474 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.1656. Min Act: -0.0001

Data Index: 1559378 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1044535 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.1300. Min Act: -0.0001

Data Index: 87557 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.2881. Min Range: -1.2881

Max Act: 0.9811. Min Act: -0.0001

Data Index: 522787 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0613. Min Act: -0.0001

Data Index: 697819 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0779. Min Act: -0.0001

Data Index: 692383 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0450. Min Act: -0.0001

Data Index: 349619 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.1221. Min Act: -0.0001

Data Index: 1354186 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0580. Min Act: -0.0001

Data Index: 845740 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0395. Min Act: -0.0001

Data Index: 113608 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0442. Min Act: -0.0001

Data Index: 613882 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0569. Min Act: -0.0001

Data Index: 239462 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0429. Min Act: -0.0001

Data Index: 940735 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1140668 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0435. Min Act: -0.0001

Data Index: 311668 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0446. Min Act: -0.0001

Data Index: 555920 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0136. Min Act: -0.0001

Data Index: 431086 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0090. Min Act: -0.0001

Data Index: 590359 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.2881. Min Range: -1.2881

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1000847 (C4 (Web Text))

Max Activating Token Index: 27