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

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

Neuron 3169 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: 1.9393. Min Range: -1.9393

Max Act: 1.9393. Min Act: -0.0001

Data Index: 1053988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.9053. Min Act: -0.0001

Data Index: 484454 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.7769. Min Act: -0.0001

Data Index: 280720 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.9393. Min Range: -1.9393

Max Act: 0.9497. Min Act: -0.0001

Data Index: 957550 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5791. Min Act: -0.0001

Data Index: 531662 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.6608. Min Act: -0.0001

Data Index: 746231 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.8320. Min Act: -0.0001

Data Index: 1311872 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5688. Min Act: -0.0001

Data Index: 605820 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.4402. Min Act: -0.0001

Data Index: 131492 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.4447. Min Act: -0.0001

Data Index: 343435 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.6598. Min Act: -0.0001

Data Index: 724057 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.4750. Min Act: -0.0001

Data Index: 1193968 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5952. Min Act: -0.0001

Data Index: 970934 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.3848. Min Act: -0.0001

Data Index: 1347203 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.4944. Min Act: -0.0001

Data Index: 962835 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5249. Min Act: -0.0001

Data Index: 344545 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5694. Min Act: -0.0001

Data Index: 384934 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.4767. Min Act: -0.0001

Data Index: 43067 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.5125. Min Act: -0.0001

Data Index: 814416 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.9393. Min Range: -1.9393

Max Act: 1.6911. Min Act: -0.0001

Data Index: 822374 (C4 (Web Text))

Max Activating Token Index: 475