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

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

Neuron 2655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8711. Min Act: -0.0001

Data Index: 1055274 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7496. Min Act: -0.0001

Data Index: 785720 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1021337 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7804. Min Act: -0.0001

Data Index: 482640 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0001

Data Index: 828231 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7493. Min Act: -0.0001

Data Index: 1335394 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7892. Min Act: -0.0001

Data Index: 54487 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7641. Min Act: -0.0001

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7620. Min Act: -0.0001

Data Index: 1125704 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8305. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1222123 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7671. Min Act: -0.0001

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7205. Min Act: -0.0001

Data Index: 173539 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6908. Min Act: -0.0001

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1084967 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7298. Min Act: -0.0001

Data Index: 430047 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7741. Min Act: -0.0001

Data Index: 457247 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6786. Min Act: -0.0001

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7290. Min Act: -0.0001

Data Index: 273999 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6923. Min Act: -0.0001

Data Index: 193613 (C4 (Web Text))

Max Activating Token Index: 810