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

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

Neuron 1685 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0847. Min Range: -2.0847

Max Act: 2.0207. Min Act: -0.0000

Data Index: 125424 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1180292 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.0847. Min Range: -2.0847

Max Act: 2.0847. Min Act: -0.0000

Data Index: 1500150 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1540260 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1451624 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.8567. Min Act: -0.0000

Data Index: 333030 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.8374. Min Act: -0.0000

Data Index: 720498 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1358446 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1492569 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.7001. Min Act: -0.0000

Data Index: 922116 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1465845 (Python Code)

Max Activating Token Index: 471

Text #11

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1440243 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6955. Min Act: -0.0000

Data Index: 62488 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6882. Min Act: -0.0000

Data Index: 78530 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1656928 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.7412. Min Act: -0.0000

Data Index: 257645 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6456. Min Act: -0.0000

Data Index: 133478 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.5587. Min Act: -0.0000

Data Index: 230365 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.5456. Min Act: -0.0000

Data Index: 909 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 2.0847. Min Range: -2.0847

Max Act: 1.6493. Min Act: -0.0000

Data Index: 1317108 (C4 (Web Text))

Max Activating Token Index: 100