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

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

Neuron 4865 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6614. Min Range: -2.6614

Max Act: 2.6614. Min Act: -0.0000

Data Index: 1240477 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.6761. Min Act: -0.0000

Data Index: 649786 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.6927. Min Act: -0.0001

Data Index: 638889 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.5615. Min Act: -0.0000

Data Index: 928685 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.6782. Min Act: -0.0000

Data Index: 817672 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4364. Min Act: -0.0000

Data Index: 347910 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4568. Min Act: -0.0000

Data Index: 141120 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.5430. Min Act: -0.0000

Data Index: 859919 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.5689. Min Act: -0.0000

Data Index: 639581 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1032062 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4737. Min Act: -0.0000

Data Index: 870238 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.3856. Min Act: -0.0000

Data Index: 990156 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4210. Min Act: -0.0000

Data Index: 249986 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4136. Min Act: -0.0000

Data Index: 302297 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4487. Min Act: -0.0000

Data Index: 433519 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1049313 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.3488. Min Act: -0.0000

Data Index: 787042 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4306. Min Act: -0.0000

Data Index: 171657 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4605. Min Act: -0.0000

Data Index: 641934 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.6614. Min Range: -2.6614

Max Act: 1.4628. Min Act: -0.0000

Data Index: 233061 (C4 (Web Text))

Max Activating Token Index: 470