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

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

Neuron 2854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.2573. Min Act: -0.0000

Data Index: 581417 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1077049 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.2568. Min Act: -0.0000

Data Index: 188908 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0325. Min Act: -0.0000

Data Index: 87821 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1213801 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.9710. Min Act: -0.0000

Data Index: 576760 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0055. Min Act: -0.0000

Data Index: 144296 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.9437. Min Act: -0.0000

Data Index: 381630 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.9495. Min Act: -0.0000

Data Index: 881917 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8163. Min Act: -0.0000

Data Index: 572082 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.9358. Min Act: -0.0000

Data Index: 126757 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1055376 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.9257. Min Act: -0.0000

Data Index: 325746 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8922. Min Act: -0.0000

Data Index: 936828 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8878. Min Act: -0.0000

Data Index: 768164 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8259. Min Act: -0.0000

Data Index: 255175 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1339943 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8081. Min Act: -0.0000

Data Index: 196121 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.7946. Min Act: -0.0000

Data Index: 400775 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 1.2573. Min Range: -1.2573

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1256044 (C4 (Web Text))

Max Activating Token Index: 750