Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 889 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.5177. Min Act: -0.1700

Data Index: 1457845 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.2990. Min Act: -0.1700

Data Index: 1516220 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.2365. Min Act: -0.1700

Data Index: 1452311 (Python Code)

Max Activating Token Index: 644

Text #3

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.2052. Min Act: -0.1700

Data Index: 1570986 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.2052. Min Act: -0.1700

Data Index: 1437706 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.2052. Min Act: -0.1700

Data Index: 1364815 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1394914 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.1740. Min Act: -0.1700

Data Index: 1497341 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.1115. Min Act: -0.1700

Data Index: 1447413 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1437984 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1597226 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.1115. Min Act: -0.1700

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1580466 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1437776 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0490. Min Act: -0.1700

Data Index: 1494584 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0490. Min Act: -0.1700

Data Index: 1471489 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0177. Min Act: -0.1700

Data Index: 1527329 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0490. Min Act: -0.1700

Data Index: 1535116 (Python Code)

Max Activating Token Index: 332

Text #18

Max Range: 5.5177. Min Range: -5.5177

Max Act: 5.0490. Min Act: -0.1700

Data Index: 1537910 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 5.5177. Min Range: -5.5177

Max Act: 4.9865. Min Act: -0.1700

Data Index: 1451102 (Python Code)

Max Activating Token Index: 659