Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.4947. Min Act: -0.0000

Data Index: 471931 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2670. Min Act: -0.0000

Data Index: 475602 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2545. Min Act: -0.0000

Data Index: 1175176 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.1431. Min Act: -0.0000

Data Index: 472752 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9548. Min Act: -0.0000

Data Index: 1041619 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.0897. Min Act: -0.0000

Data Index: 560814 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.2449. Min Act: -0.0000

Data Index: 462914 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 4.4947. Min Range: -4.4947

Max Act: 4.3223. Min Act: -0.0000

Data Index: 708203 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.9825. Min Act: -0.0000

Data Index: 65840 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.8399. Min Act: -0.0000

Data Index: 699646 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.6514. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.6274. Min Act: -0.0000

Data Index: 986450 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.6328. Min Act: -0.0000

Data Index: 1314176 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.5857. Min Act: -0.0000

Data Index: 260595 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.5664. Min Act: -0.0000

Data Index: 1315846 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.5636. Min Act: -0.0000

Data Index: 1117755 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.5585. Min Act: -0.0000

Data Index: 1269280 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.5717. Min Act: -0.0000

Data Index: 1182474 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.2441. Min Act: -0.0000

Data Index: 434000 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 4.4947. Min Range: -4.4947

Max Act: 3.3859. Min Act: -0.0000

Data Index: 900114 (C4 (Web Text))

Max Activating Token Index: 842