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

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

Neuron 2548 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: 1.8388. Min Range: -1.8388

Max Act: 1.7706. Min Act: -0.0000

Data Index: 712846 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.8388. Min Act: -0.0000

Data Index: 521153 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1320715 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.2485. Min Act: -0.0000

Data Index: 109511 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.1642. Min Act: -0.0000

Data Index: 786548 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1138326 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.2214. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.1082. Min Act: -0.0000

Data Index: 504029 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0734. Min Act: -0.0000

Data Index: 497814 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0709. Min Act: -0.0000

Data Index: 214906 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.1217. Min Act: -0.0000

Data Index: 579295 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0438. Min Act: -0.0000

Data Index: 431770 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0479. Min Act: -0.0000

Data Index: 590891 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.1099. Min Act: -0.0000

Data Index: 998102 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0983. Min Act: -0.0000

Data Index: 164725 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0220. Min Act: -0.0000

Data Index: 720792 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0263. Min Act: -0.0000

Data Index: 566941 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0258. Min Act: -0.0000

Data Index: 147638 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.0142. Min Act: -0.0000

Data Index: 788077 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.8388. Min Range: -1.8388

Max Act: 0.9612. Min Act: -0.0000

Data Index: 106064 (C4 (Web Text))

Max Activating Token Index: 288