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

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

Neuron 4213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.2795. Min Act: -0.0000

Data Index: 815749 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.2677. Min Act: -0.0001

Data Index: 774458 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.1056. Min Act: -0.0001

Data Index: 406447 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.1428. Min Act: -0.0001

Data Index: 350494 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.0413. Min Act: -0.0000

Data Index: 183390 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.2795. Min Range: -3.2795

Max Act: 3.0285. Min Act: -0.0001

Data Index: 66642 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.8753. Min Act: -0.0001

Data Index: 1112144 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.8917. Min Act: -0.0001

Data Index: 623168 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.8279. Min Act: -0.0001

Data Index: 1147704 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.7934. Min Act: -0.0001

Data Index: 186208 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.6530. Min Act: -0.0000

Data Index: 292405 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.9038. Min Act: -0.0000

Data Index: 219279 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.5043. Min Act: -0.0001

Data Index: 61264 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.5955. Min Act: -0.0001

Data Index: 1171180 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.7542. Min Act: -0.0001

Data Index: 1155139 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.8377. Min Act: -0.0000

Data Index: 1107973 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.6946. Min Act: -0.0001

Data Index: 363797 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.5742. Min Act: -0.0000

Data Index: 627240 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.8165. Min Act: -0.0001

Data Index: 102557 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 3.2795. Min Range: -3.2795

Max Act: 2.7540. Min Act: -0.0001

Data Index: 860254 (C4 (Web Text))

Max Activating Token Index: 656