Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2647 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.8815. Min Act: -0.0001

Data Index: 423263 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7229. Min Act: -0.0001

Data Index: 322685 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7918. Min Act: -0.0001

Data Index: 388467 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7243. Min Act: -0.0001

Data Index: 313045 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7483. Min Act: -0.0001

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6927. Min Act: -0.0001

Data Index: 299709 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7386. Min Act: -0.0001

Data Index: 545636 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7472. Min Act: -0.0001

Data Index: 352485 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1259448 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7093. Min Act: -0.0001

Data Index: 666546 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6694. Min Act: -0.0001

Data Index: 659470 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.7120. Min Act: -0.0001

Data Index: 426399 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1301288 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6675. Min Act: -0.0001

Data Index: 423705 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1314704 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6805. Min Act: -0.0001

Data Index: 876941 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6277. Min Act: -0.0001

Data Index: 485376 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6400. Min Act: -0.0001

Data Index: 41525 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1323602 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.8815. Min Range: -0.8815

Max Act: 0.6911. Min Act: -0.0001

Data Index: 503773 (C4 (Web Text))

Max Activating Token Index: 689