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

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

Neuron 1225 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: 4.2084. Min Range: -4.2084

Max Act: 4.2084. Min Act: -0.1700

Data Index: 1609445 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0972. Min Act: -0.1700

Data Index: 1515535 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0617. Min Act: -0.1700

Data Index: 1545548 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0139. Min Act: -0.1700

Data Index: 1361614 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 4.2084. Min Range: -4.2084

Max Act: 4.0581. Min Act: -0.1700

Data Index: 1629136 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9920. Min Act: -0.1700

Data Index: 1415845 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9468. Min Act: -0.1700

Data Index: 1437449 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9566. Min Act: -0.1700

Data Index: 1597541 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9451. Min Act: -0.1700

Data Index: 1373020 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9095. Min Act: -0.1700

Data Index: 1588337 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9347. Min Act: -0.1700

Data Index: 1656989 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9204. Min Act: -0.1700

Data Index: 1499115 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.9187. Min Act: -0.1700

Data Index: 1540443 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8771. Min Act: -0.1700

Data Index: 1490275 (Python Code)

Max Activating Token Index: 706

Text #14

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8803. Min Act: -0.1700

Data Index: 1553244 (Python Code)

Max Activating Token Index: 615

Text #15

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1493711 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8923. Min Act: -0.1700

Data Index: 1452978 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8472. Min Act: -0.1700

Data Index: 1413608 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8691. Min Act: -0.1700

Data Index: 1418830 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 4.2084. Min Range: -4.2084

Max Act: 3.8341. Min Act: -0.1700

Data Index: 1514920 (Python Code)

Max Activating Token Index: 710