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

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

Neuron 804 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1760. Min Act: -0.0001

Data Index: 600219 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1694. Min Act: -0.0001

Data Index: 314263 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1145591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1191391 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1530. Min Act: -0.0001

Data Index: 425727 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1525. Min Act: -0.0001

Data Index: 321898 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1509. Min Act: -0.0001

Data Index: 270939 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1311864 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1489. Min Act: -0.0001

Data Index: 111208 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1248479 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1421. Min Act: -0.0001

Data Index: 877964 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1455. Min Act: -0.0001

Data Index: 854403 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1414. Min Act: -0.0001

Data Index: 172842 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1237569 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1380. Min Act: -0.0001

Data Index: 593666 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1477. Min Act: -0.0001

Data Index: 295469 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1415. Min Act: -0.0001

Data Index: 12159 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1466. Min Act: -0.0001

Data Index: 512098 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1284674 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.1760. Min Range: -0.1760

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1244072 (C4 (Web Text))

Max Activating Token Index: 804