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

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

Neuron 3534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.5464. Min Act: -0.0001

Data Index: 462275 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.4772. Min Act: -0.0001

Data Index: 1220541 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.5011. Min Act: -0.0001

Data Index: 1322644 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.4676. Min Act: -0.0001

Data Index: 870134 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.4599. Min Act: -0.0001

Data Index: 454961 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.3948. Min Act: -0.0001

Data Index: 1135806 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.4354. Min Act: -0.0001

Data Index: 1283842 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.4051. Min Act: -0.0001

Data Index: 40379 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2839. Min Act: -0.0001

Data Index: 387718 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.3289. Min Act: -0.0001

Data Index: 513591 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2757. Min Act: -0.0001

Data Index: 819745 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.3825. Min Act: -0.0001

Data Index: 678826 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2570. Min Act: -0.0000

Data Index: 515470 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2854. Min Act: -0.0001

Data Index: 350938 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2318. Min Act: -0.0001

Data Index: 852462 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2592. Min Act: -0.0001

Data Index: 1113303 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2136. Min Act: -0.0001

Data Index: 740884 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.2108. Min Act: -0.0000

Data Index: 878737 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.1730. Min Act: -0.0000

Data Index: 252764 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.5464. Min Range: -1.5464

Max Act: 1.1620. Min Act: -0.0001

Data Index: 360326 (C4 (Web Text))

Max Activating Token Index: 1016