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

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

Neuron 1343 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.2647. Min Range: -10.2647

Max Act: 10.2647. Min Act: -0.0000

Data Index: 1586670 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.8874. Min Act: -0.0000

Data Index: 1621426 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.8531. Min Act: -0.0000

Data Index: 1332515 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.8823. Min Act: -0.0000

Data Index: 1305216 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.6661. Min Act: -0.0000

Data Index: 21784 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.6721. Min Act: -0.0000

Data Index: 551417 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.1595. Min Act: -0.0000

Data Index: 1314216 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.5002. Min Act: -0.0000

Data Index: 1244671 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.7448. Min Act: -0.0000

Data Index: 1217785 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.4883. Min Act: -0.0000

Data Index: 169397 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.1909. Min Act: -0.0000

Data Index: 615890 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 10.2647. Min Range: -10.2647

Max Act: 8.9462. Min Act: -0.0000

Data Index: 128434 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 10.2647. Min Range: -10.2647

Max Act: 8.9344. Min Act: -0.0000

Data Index: 202035 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.2778. Min Act: -0.0000

Data Index: 1141873 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.2135. Min Act: 0.0000

Data Index: 1336683 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.2126. Min Act: -0.0000

Data Index: 315912 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.1969. Min Act: -0.0000

Data Index: 320906 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 10.2647. Min Range: -10.2647

Max Act: 8.8084. Min Act: -0.0000

Data Index: 827889 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.4873. Min Act: -0.0000

Data Index: 55294 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 10.2647. Min Range: -10.2647

Max Act: 9.1468. Min Act: -0.0000

Data Index: 339403 (C4 (Web Text))

Max Activating Token Index: 433