Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2792. Min Range: -2.2792

Max Act: 2.2792. Min Act: -0.0000

Data Index: 1491519 (Python Code)

Max Activating Token Index: 469

Text #1

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.9386. Min Act: -0.0000

Data Index: 1549150 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1410204 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1652057 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1519880 (Python Code)

Max Activating Token Index: 912

Text #5

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.7171. Min Act: -0.0000

Data Index: 1447678 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.7452. Min Act: -0.0000

Data Index: 1384054 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1598122 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1374591 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1400305 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1654874 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1492775 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1575988 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1428954 (Python Code)

Max Activating Token Index: 539

Text #14

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1555918 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1624723 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4351. Min Act: -0.0000

Data Index: 1438754 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1494702 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1603250 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1386236 (Python Code)

Max Activating Token Index: 668