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

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

Neuron 212 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: 0.6574. Min Range: -0.6574

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1365340 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6574. Min Act: -0.0000

Data Index: 696531 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1450750 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6372. Min Act: -0.0000

Data Index: 711198 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6398. Min Act: -0.0000

Data Index: 141992 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1023934 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1205370 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6185. Min Act: -0.0000

Data Index: 195005 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1200915 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1293904 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5771. Min Act: -0.0000

Data Index: 562844 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1155246 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1581209 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1482343 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5947. Min Act: -0.0000

Data Index: 205676 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5573. Min Act: -0.0000

Data Index: 204734 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5356. Min Act: -0.0000

Data Index: 856414 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5916. Min Act: -0.0000

Data Index: 113411 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5534. Min Act: -0.0000

Data Index: 553911 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5480. Min Act: -0.0000

Data Index: 894704 (C4 (Web Text))

Max Activating Token Index: 516