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

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

Neuron 1873 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7538. Min Range: -4.7538

Max Act: 4.7538. Min Act: -0.0001

Data Index: 1385020 (Python Code)

Max Activating Token Index: 506

Text #1

Max Range: 4.7538. Min Range: -4.7538

Max Act: 4.0849. Min Act: -0.0001

Data Index: 1548318 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.8963. Min Act: -0.0001

Data Index: 1628862 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.7197. Min Act: -0.0001

Data Index: 1551198 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.3849. Min Act: -0.0001

Data Index: 1409426 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.5526. Min Act: -0.0001

Data Index: 1453177 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1611842 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.2144. Min Act: -0.0001

Data Index: 1387730 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.3210. Min Act: -0.0001

Data Index: 1056326 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.1874. Min Act: -0.0001

Data Index: 233485 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.3386. Min Act: -0.0001

Data Index: 1476245 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.1770. Min Act: -0.0001

Data Index: 831435 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.3026. Min Act: -0.0001

Data Index: 1470148 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.4147. Min Act: -0.0001

Data Index: 1470035 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 4.7538. Min Range: -4.7538

Max Act: 2.8921. Min Act: -0.0001

Data Index: 1218270 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.1670. Min Act: -0.0001

Data Index: 1000388 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.2861. Min Act: -0.0001

Data Index: 1592974 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.1467. Min Act: -0.0001

Data Index: 1509497 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.2824. Min Act: -0.0000

Data Index: 1494939 (Python Code)

Max Activating Token Index: 454

Text #19

Max Range: 4.7538. Min Range: -4.7538

Max Act: 3.3973. Min Act: -0.0001

Data Index: 1483907 (Python Code)

Max Activating Token Index: 142