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

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

Neuron 5111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8033. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.7050. Min Act: -0.0000

Data Index: 969299 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6949. Min Act: -0.0000

Data Index: 630616 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6192. Min Act: -0.0000

Data Index: 423191 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6570. Min Act: -0.0000

Data Index: 972001 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5995. Min Act: -0.0000

Data Index: 503624 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6516. Min Act: -0.0000

Data Index: 51105 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5893. Min Act: -0.0000

Data Index: 58960 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5893. Min Act: -0.0000

Data Index: 455329 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1169522 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1230701 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5871. Min Act: -0.0000

Data Index: 64747 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5628. Min Act: -0.0000

Data Index: 181357 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1180080 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5724. Min Act: -0.0000

Data Index: 617363 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5777. Min Act: -0.0000

Data Index: 11648 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5917. Min Act: -0.0000

Data Index: 981339 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5326. Min Act: -0.0000

Data Index: 638924 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5660. Min Act: -0.0000

Data Index: 839201 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5650. Min Act: -0.0000

Data Index: 35261 (C4 (Web Text))

Max Activating Token Index: 709