Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1110 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.1095. Min Act: -0.1700

Data Index: 1522755 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0157. Min Act: -0.1700

Data Index: 1650885 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0157. Min Act: -0.1700

Data Index: 1632706 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0157. Min Act: -0.1700

Data Index: 1449036 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9531. Min Act: -0.1700

Data Index: 1490247 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9844. Min Act: -0.1700

Data Index: 1499292 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9219. Min Act: -0.1700

Data Index: 1385125 (Python Code)

Max Activating Token Index: 659

Text #7

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9219. Min Act: -0.1700

Data Index: 1643344 (Python Code)

Max Activating Token Index: 242

Text #8

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9531. Min Act: -0.1700

Data Index: 1449592 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9219. Min Act: -0.1700

Data Index: 1561421 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8593. Min Act: -0.1700

Data Index: 1519512 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8906. Min Act: -0.1700

Data Index: 1627852 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8593. Min Act: -0.1700

Data Index: 1639910 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8593. Min Act: -0.1700

Data Index: 1454722 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8593. Min Act: -0.1700

Data Index: 1443311 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7968. Min Act: -0.1700

Data Index: 1493673 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7968. Min Act: -0.1700

Data Index: 1543352 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1543577 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1483262 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1649744 (Python Code)

Max Activating Token Index: 29