Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3149 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1131. Min Range: -3.1131

Max Act: 3.1131. Min Act: -0.0001

Data Index: 1498077 (Python Code)

Max Activating Token Index: 685

Text #1

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.7690. Min Act: -0.0001

Data Index: 1598426 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.6182. Min Act: -0.0001

Data Index: 1385254 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.7162. Min Act: -0.0001

Data Index: 1361131 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.6789. Min Act: -0.0001

Data Index: 1472274 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.5325. Min Act: -0.0001

Data Index: 1384741 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.5033. Min Act: -0.0001

Data Index: 1553134 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.3077. Min Act: -0.0001

Data Index: 1602474 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.4500. Min Act: -0.0001

Data Index: 1384276 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.4413. Min Act: -0.0001

Data Index: 1625665 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.3156. Min Act: -0.0001

Data Index: 1519705 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.3556. Min Act: -0.0001

Data Index: 1403302 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.2076. Min Act: -0.0001

Data Index: 1625451 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.3374. Min Act: -0.0001

Data Index: 1368899 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.2719. Min Act: -0.0001

Data Index: 1467801 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.2067. Min Act: -0.0001

Data Index: 1425724 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.3035. Min Act: -0.0001

Data Index: 1633569 (Python Code)

Max Activating Token Index: 817

Text #17

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.1802. Min Act: -0.0001

Data Index: 1507280 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.2977. Min Act: -0.0001

Data Index: 1502939 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 3.1131. Min Range: -3.1131

Max Act: 2.2368. Min Act: -0.0001

Data Index: 1406615 (Python Code)

Max Activating Token Index: 397