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

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

Neuron 4738 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 179948 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5188. Min Act: -0.0000

Data Index: 22363 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4603. Min Act: -0.0000

Data Index: 45159 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5077. Min Act: -0.0000

Data Index: 979057 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1169885 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4690. Min Act: -0.0000

Data Index: 633927 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1254168 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4598. Min Act: -0.0000

Data Index: 630574 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4272. Min Act: -0.0000

Data Index: 966036 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4296. Min Act: -0.0000

Data Index: 671847 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4246. Min Act: -0.0000

Data Index: 543413 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1279479 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3887. Min Act: -0.0000

Data Index: 272033 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1117702 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1253603 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4012. Min Act: -0.0000

Data Index: 8794 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3874. Min Act: -0.0000

Data Index: 863112 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3728. Min Act: -0.0000

Data Index: 611126 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3996. Min Act: -0.0000

Data Index: 989791 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.3866. Min Act: -0.0000

Data Index: 621275 (C4 (Web Text))

Max Activating Token Index: 523