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

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

Neuron 409 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1907. Min Range: -4.1907

Max Act: 4.1907. Min Act: -0.0000

Data Index: 1479100 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.6062. Min Act: -0.0000

Data Index: 1571032 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.6635. Min Act: -0.0000

Data Index: 1411849 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.4328. Min Act: -0.0000

Data Index: 1511308 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.2895. Min Act: -0.0000

Data Index: 1449397 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.4832. Min Act: -0.0000

Data Index: 1480181 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 4.1907. Min Range: -4.1907

Max Act: 2.6635. Min Act: -0.0000

Data Index: 993933 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.0920. Min Act: -0.0000

Data Index: 1414530 (Python Code)

Max Activating Token Index: 663

Text #8

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.3439. Min Act: -0.0000

Data Index: 153170 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 4.1907. Min Range: -4.1907

Max Act: 2.9757. Min Act: -0.0000

Data Index: 1465192 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.2565. Min Act: -0.0000

Data Index: 1520180 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.2166. Min Act: -0.0000

Data Index: 1449237 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.0329. Min Act: -0.0000

Data Index: 1559074 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.1575. Min Act: -0.0000

Data Index: 1584238 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 4.1907. Min Range: -4.1907

Max Act: 2.9942. Min Act: -0.0000

Data Index: 1643599 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.1288. Min Act: -0.0000

Data Index: 1639844 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.2336. Min Act: -0.0000

Data Index: 1559835 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 4.1907. Min Range: -4.1907

Max Act: 2.8189. Min Act: -0.0000

Data Index: 1640514 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 4.1907. Min Range: -4.1907

Max Act: 2.9272. Min Act: -0.0000

Data Index: 1458508 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 4.1907. Min Range: -4.1907

Max Act: 3.0524. Min Act: -0.0000

Data Index: 1402684 (Python Code)

Max Activating Token Index: 305