Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1355098 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.0388. Min Range: -1.0388

Max Act: 1.0388. Min Act: -0.0001

Data Index: 922565 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9256. Min Act: -0.0001

Data Index: 389589 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1269969 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.9171. Min Act: -0.0001

Data Index: 893010 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7770. Min Act: -0.0001

Data Index: 10068 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7799. Min Act: -0.0001

Data Index: 486036 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8157. Min Act: -0.0001

Data Index: 705797 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8348. Min Act: -0.0001

Data Index: 835528 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7490. Min Act: -0.0001

Data Index: 803927 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8535. Min Act: -0.0001

Data Index: 201281 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7112. Min Act: -0.0001

Data Index: 1228475 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1357111 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1168889 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7978. Min Act: -0.0001

Data Index: 121460 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.8258. Min Act: -0.0001

Data Index: 220433 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1047697 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7913. Min Act: -0.0001

Data Index: 492133 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.7471. Min Act: -0.0001

Data Index: 292086 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.0388. Min Range: -1.0388

Max Act: 0.6944. Min Act: -0.0001

Data Index: 393622 (C4 (Web Text))

Max Activating Token Index: 615