Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2251 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1259491 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2727. Min Act: -0.0001

Data Index: 213288 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2832. Min Act: -0.0001

Data Index: 859477 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2346. Min Act: -0.0001

Data Index: 538393 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1090024 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2438. Min Act: -0.0001

Data Index: 854200 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2457. Min Act: -0.0001

Data Index: 59789 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2336. Min Act: -0.0001

Data Index: 310518 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2362. Min Act: -0.0001

Data Index: 267875 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2379. Min Act: -0.0001

Data Index: 969626 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2283. Min Act: -0.0001

Data Index: 600809 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1292241 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2133. Min Act: -0.0001

Data Index: 15527 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2141. Min Act: -0.0001

Data Index: 528101 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2386. Min Act: -0.0001

Data Index: 620126 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2281. Min Act: -0.0001

Data Index: 291067 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2121. Min Act: -0.0001

Data Index: 434689 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1527720 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2039. Min Act: -0.0001

Data Index: 29412 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.3643. Min Range: -0.3643

Max Act: 0.2039. Min Act: -0.0001

Data Index: 365041 (C4 (Web Text))

Max Activating Token Index: 3