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

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

Neuron 808 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1901. Min Act: -0.0003

Data Index: 869156 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1942. Min Act: -0.0003

Data Index: 293238 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1788. Min Act: -0.0003

Data Index: 513107 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1636. Min Act: -0.0003

Data Index: 1418 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1883. Min Act: -0.0003

Data Index: 977713 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1692. Min Act: -0.0003

Data Index: 127768 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1582. Min Act: -0.0003

Data Index: 1060002 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1729. Min Act: -0.0003

Data Index: 1234293 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1510. Min Act: -0.0003

Data Index: 685172 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1597. Min Act: -0.0003

Data Index: 1278777 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1506. Min Act: -0.0003

Data Index: 70047 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1524. Min Act: -0.0003

Data Index: 780172 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1570. Min Act: -0.0003

Data Index: 574359 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1458. Min Act: -0.0003

Data Index: 591446 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1465. Min Act: -0.0003

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1540. Min Act: -0.0003

Data Index: 398001 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1381. Min Act: -0.0003

Data Index: 401573 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1652. Min Act: -0.0003

Data Index: 1014544 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1500. Min Act: -0.0003

Data Index: 1327247 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1649. Min Act: -0.0003

Data Index: 385486 (C4 (Web Text))

Max Activating Token Index: 691