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

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

Neuron 1588 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1186643 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1168825 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4590. Min Act: -0.0001

Data Index: 73434 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3922. Min Act: -0.0001

Data Index: 666275 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3248. Min Act: -0.0001

Data Index: 217602 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1207699 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3003. Min Act: -0.0001

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3169. Min Act: -0.0001

Data Index: 1186431 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2861. Min Act: -0.0001

Data Index: 872254 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3038. Min Act: -0.0001

Data Index: 396693 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3019. Min Act: -0.0001

Data Index: 364946 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3132. Min Act: -0.0001

Data Index: 350269 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2671. Min Act: -0.0001

Data Index: 846220 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1126405 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2674. Min Act: -0.0001

Data Index: 385378 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2670. Min Act: -0.0001

Data Index: 330337 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3195. Min Act: -0.0001

Data Index: 571046 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2820. Min Act: -0.0001

Data Index: 951186 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2921. Min Act: -0.0001

Data Index: 106904 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.2684. Min Act: -0.0001

Data Index: 266812 (C4 (Web Text))

Max Activating Token Index: 150