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

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

Neuron 3078 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.5538. Min Act: -0.0000

Data Index: 691380 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.6598. Min Act: -0.0000

Data Index: 674983 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1036483 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1093030 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.4283. Min Act: -0.0000

Data Index: 124934 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.4014. Min Act: -0.0000

Data Index: 496837 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.3229. Min Act: -0.0000

Data Index: 928593 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2444. Min Act: -0.0000

Data Index: 576138 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1180584 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1348471 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.1872. Min Act: -0.0000

Data Index: 173241 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1081259 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1349047 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2847. Min Act: -0.0000

Data Index: 637044 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.2053. Min Act: -0.0000

Data Index: 807183 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.0827. Min Act: -0.0000

Data Index: 571512 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.3951. Min Act: -0.0000

Data Index: 1053797 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1112272 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.6598. Min Range: -1.6598

Max Act: 0.9930. Min Act: -0.0000

Data Index: 822451 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.6598. Min Range: -1.6598

Max Act: 1.1557. Min Act: -0.0000

Data Index: 632833 (C4 (Web Text))

Max Activating Token Index: 822