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

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

Neuron 978 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: 0.6734. Min Range: -0.6734

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1057730 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.6383. Min Act: -0.0000

Data Index: 60392 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5970. Min Act: -0.0000

Data Index: 421671 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5459. Min Act: -0.0000

Data Index: 355306 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5312. Min Act: -0.0000

Data Index: 103596 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.5637. Min Act: -0.0000

Data Index: 221629 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4761. Min Act: -0.0000

Data Index: 481174 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4963. Min Act: -0.0000

Data Index: 918465 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4230. Min Act: -0.0000

Data Index: 35501 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4628. Min Act: -0.0000

Data Index: 575526 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4920. Min Act: -0.0000

Data Index: 211922 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4404. Min Act: -0.0000

Data Index: 480440 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4697. Min Act: -0.0000

Data Index: 510273 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4495. Min Act: -0.0000

Data Index: 927651 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4288. Min Act: -0.0000

Data Index: 913936 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4012. Min Act: -0.0000

Data Index: 419678 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4034. Min Act: -0.0000

Data Index: 560985 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.4301. Min Act: -0.0000

Data Index: 925728 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3951. Min Act: -0.0000

Data Index: 371997 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.6734. Min Range: -0.6734

Max Act: 0.3558. Min Act: -0.0000

Data Index: 399170 (C4 (Web Text))

Max Activating Token Index: 285