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

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

Neuron 380 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: 3.8886. Min Range: -3.8886

Max Act: 3.8886. Min Act: -0.1700

Data Index: 262219 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8708. Min Act: -0.1700

Data Index: 197800 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8583. Min Act: -0.1700

Data Index: 550462 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8499. Min Act: -0.1700

Data Index: 294750 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8117. Min Act: -0.1700

Data Index: 322495 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.7741. Min Act: -0.1700

Data Index: 1327527 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.7592. Min Act: -0.1700

Data Index: 83777 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6934. Min Act: -0.1700

Data Index: 1323515 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6903. Min Act: -0.1700

Data Index: 759703 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6605. Min Act: -0.1700

Data Index: 583885 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6699. Min Act: -0.1700

Data Index: 277325 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6860. Min Act: -0.1700

Data Index: 582250 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6488. Min Act: -0.1700

Data Index: 606350 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6470. Min Act: -0.1700

Data Index: 1221328 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6334. Min Act: -0.1700

Data Index: 78477 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6220. Min Act: -0.1700

Data Index: 910173 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6153. Min Act: -0.1700

Data Index: 880105 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6107. Min Act: -0.1700

Data Index: 678592 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.5954. Min Act: -0.1700

Data Index: 1175771 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.5947. Min Act: -0.1700

Data Index: 608001 (C4 (Web Text))

Max Activating Token Index: 849