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

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

Neuron 5093 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: 0.8669. Min Range: -0.8669

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1140711 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.8669. Min Act: -0.0000

Data Index: 621395 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.3801. Min Act: -0.0000

Data Index: 687781 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1257541 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1075823 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1143899 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0685. Min Act: -0.0000

Data Index: 767408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0233. Min Act: -0.0000

Data Index: 306641 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1440608 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0353. Min Act: -0.0000

Data Index: 920900 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0381. Min Act: -0.0000

Data Index: 788901 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1403598 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1622870 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0302. Min Act: -0.0000

Data Index: 1615490 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1581537 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0288. Min Act: -0.0000

Data Index: 1583550 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1366451 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1364644 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1448729 (Python Code)

Max Activating Token Index: 621

Text #19

Max Range: 0.8669. Min Range: -0.8669

Max Act: 0.0309. Min Act: -0.0000

Data Index: 345274 (C4 (Web Text))

Max Activating Token Index: 136