Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 662 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.0519. Min Range: -5.0519

Max Act: 5.0519. Min Act: -0.1700

Data Index: 1403469 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 5.0519. Min Range: -5.0519

Max Act: 5.0466. Min Act: -0.1700

Data Index: 1604246 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.9118. Min Act: -0.1700

Data Index: 1638042 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1475315 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8962. Min Act: -0.1700

Data Index: 1612073 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.9205. Min Act: -0.1700

Data Index: 1369065 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8744. Min Act: -0.1700

Data Index: 1591050 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8799. Min Act: -0.1700

Data Index: 1387126 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8755. Min Act: -0.1700

Data Index: 1445567 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8809. Min Act: -0.1700

Data Index: 1373105 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8859. Min Act: -0.1700

Data Index: 1618247 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8766. Min Act: -0.1700

Data Index: 1615119 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8846. Min Act: -0.1700

Data Index: 1590398 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8877. Min Act: -0.1700

Data Index: 1550663 (Python Code)

Max Activating Token Index: 199

Text #14

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8685. Min Act: -0.1700

Data Index: 1641217 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8484. Min Act: -0.1700

Data Index: 1484058 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8600. Min Act: -0.1700

Data Index: 1571733 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8729. Min Act: -0.1700

Data Index: 1625457 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8672. Min Act: -0.1700

Data Index: 1392290 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 5.0519. Min Range: -5.0519

Max Act: 4.8528. Min Act: -0.1700

Data Index: 1366556 (Python Code)

Max Activating Token Index: 238