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

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

Neuron 4797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0000

Data Index: 355173 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4090. Min Act: -0.0000

Data Index: 630370 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4122. Min Act: -0.0000

Data Index: 370549 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3713. Min Act: -0.0000

Data Index: 868132 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3598. Min Act: -0.0000

Data Index: 902878 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3623. Min Act: -0.0000

Data Index: 664352 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3450. Min Act: -0.0000

Data Index: 500552 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3269. Min Act: -0.0000

Data Index: 213644 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3485. Min Act: -0.0000

Data Index: 687048 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3116. Min Act: -0.0000

Data Index: 191680 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3102. Min Act: -0.0000

Data Index: 126740 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1348550 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3183. Min Act: -0.0000

Data Index: 995668 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1282065 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3071. Min Act: -0.0000

Data Index: 182869 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3174. Min Act: -0.0000

Data Index: 125392 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3059. Min Act: -0.0000

Data Index: 937052 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3103. Min Act: -0.0000

Data Index: 166611 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.2985. Min Act: -0.0000

Data Index: 25701 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3063. Min Act: -0.0000

Data Index: 534994 (C4 (Web Text))

Max Activating Token Index: 874