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

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

Neuron 3515 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: 0.3700. Min Range: -0.3700

Max Act: 0.3700. Min Act: -0.0001

Data Index: 478263 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2611. Min Act: -0.0001

Data Index: 77492 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2541. Min Act: -0.0001

Data Index: 566890 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2403. Min Act: -0.0001

Data Index: 499031 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2306. Min Act: -0.0001

Data Index: 1249332 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2086. Min Act: -0.0001

Data Index: 89906 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2399. Min Act: -0.0001

Data Index: 730432 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2145. Min Act: -0.0001

Data Index: 659791 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2051. Min Act: -0.0001

Data Index: 140046 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2053. Min Act: -0.0001

Data Index: 497387 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2126. Min Act: -0.0001

Data Index: 516697 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.1945. Min Act: -0.0001

Data Index: 189432 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.1907. Min Act: -0.0001

Data Index: 547553 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2104. Min Act: -0.0001

Data Index: 873576 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2069. Min Act: -0.0001

Data Index: 233813 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1157502 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2053. Min Act: -0.0001

Data Index: 760806 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.1893. Min Act: -0.0001

Data Index: 985704 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1293584 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2003. Min Act: -0.0001

Data Index: 259650 (C4 (Web Text))

Max Activating Token Index: 937